Datasets:

GlimmaryKarl
/

DualBlind

id stringlengths 21 29	problem_id stringclasses 36 values	problem_title stringclasses 35 values	suite stringclasses 11 values	topic stringclasses 7 values	domain stringclasses 35 values	difficulty stringclasses 4 values	model stringlengths 34 101	system stringclasses 1 value	prompt stringclasses 36 values	messages listlengths 3 3	canonical_answer stringclasses 35 values	is_verified bool 1 class	accuracy_score int64 100 100	turns_to_consensus int64 1 24	efficiency_index float64 0 536	cost_usd float64 0 0.24
sft-cli-run-1788555920996-954	gpqa-diamond-04	Compton Relativistic Scattering Wavelength Shift at 90-Degree Deflection	GPQA Diamond	science	Quantum Electrodynamics & Compton Scattering	Hard	gemini-2.5-flash + openrouter/free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	A high-energy gamma photon with initial incident wavelength $\lambda = 0.500\text{ pm}$ ($5.00 \times 10^{-13}\text{ m}$) undergoes Compton scattering against an initially stationary free electron ($m_e = 9.109 \times 10^{-31}\text{ kg}$). The scattered photon emerges at a scattering angle of $\theta = 90.0^\circ$ rela...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "A high-energy gamma photon wit...	lambda = 2.926 pm, Energy Fraction = 0.829	true	100	2	31.3	0.000699
sft-cli-run-1788555366949	mmlu-pro-01	Relativistic Carnot Engine Efficiency with Heat Exchange	MMLU-Pro	science	Physics & Thermodynamics	Hard	deepseek/deepseek-r1-distill-llama-70b:free + cognitivecomputations/dolphin3.0-r1-mistral-24b:free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	A hypothetical relativistic heat engine operates between two thermal reservoirs with temperatures $T_H = 1200\text{ K}$ and $T_C = 300\text{ K}$. During each cycle, the working fluid absorbs $Q_H = 4800\text{ J}$ of heat from the hot reservoir. Due to finite-time heat transfer kinetics across the boundary thermal condu...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "A hypothetical relativistic he...	Efficiency = 50%, Work = 2400 J	true	100	2	29.16	0.000548
sft-cli-run-1788555350854	mmlu-pro-01	Relativistic Carnot Engine Efficiency with Heat Exchange	MMLU-Pro	science	Physics & Thermodynamics	Hard	meta-llama/llama-3.1-8b-instruct:free + gemini-2.0-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	A hypothetical relativistic heat engine operates between two thermal reservoirs with temperatures $T_H = 1200\text{ K}$ and $T_C = 300\text{ K}$. During each cycle, the working fluid absorbs $Q_H = 4800\text{ J}$ of heat from the hot reservoir. Due to finite-time heat transfer kinetics across the boundary thermal condu...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "A hypothetical relativistic he...	Efficiency = 50%, Work = 2400 J	true	100	2	40.28	0.000565
sft-cli-run-1788554344732	mmlu-pro-01	Relativistic Carnot Engine Efficiency with Heat Exchange	MMLU-Pro	science	Physics & Thermodynamics	Hard	gemini-3.7-flash + gemini-2.5-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	A hypothetical relativistic heat engine operates between two thermal reservoirs with temperatures $T_H = 1200\text{ K}$ and $T_C = 300\text{ K}$. During each cycle, the working fluid absorbs $Q_H = 4800\text{ J}$ of heat from the hot reservoir. Due to finite-time heat transfer kinetics across the boundary thermal condu...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "A hypothetical relativistic he...	Efficiency = 50%, Work = 2400 J	true	100	2	33.89	0.000525
sft-cli-run-1788554326843	mmlu-pro-01	Relativistic Carnot Engine Efficiency with Heat Exchange	MMLU-Pro	science	Physics & Thermodynamics	Hard	gemini-3.7-flash + gemini-2.5-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	A hypothetical relativistic heat engine operates between two thermal reservoirs with temperatures $T_H = 1200\text{ K}$ and $T_C = 300\text{ K}$. During each cycle, the working fluid absorbs $Q_H = 4800\text{ J}$ of heat from the hot reservoir. Due to finite-time heat transfer kinetics across the boundary thermal condu...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "A hypothetical relativistic he...	Efficiency = 50%, Work = 2400 J	true	100	2	17.05	0.000484
sft-cli-run-1788560473930	hle-01	CRISPR-Cas9 NHEJ Indel Out-of-Frame Frameshift Probability	Humanity's Last Exam	science	Molecular Biology & CRISPR Repair Dynamics	Extreme	gemini-2.5-flash + gemini-1.5-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	In targeted genome editing, SpCas9 generates a double-strand break (DSB) 3 base pairs upstream of the NGG PAM sequence within a protein-coding exon. Repair proceeds predominantly via Non-Homologous End Joining (NHEJ) resulting in small insertions or deletions (indels). Assuming an idealized uniform prior distribution a...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "In targeted genome editing, Sp...	Frameshift Probability = 2/3, MMEJ Modulo Class = 2	true	100	3	181.66	0.000656
sft-cli-run-1788560469414	abstract-04	The Monty Hall Variant with 4 Doors and 2 Car Prizes	Game Theory	strategy	Bayesian Probability & Counterfactual Switching	Hard	gemini-2.5-flash + deepseek/deepseek-r1:free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	A game show has 4 closed doors. Behind 2 of the doors are brand-new Luxury Cars, and behind the other 2 doors are Goats. All distributions are equally likely. 1. The contestant picks Door #1. 2. The host, who knows what is behind every door, opens ONE of the remaining doors (Door #2, #3, or #4) that contains a Goat. 3...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "A game show has 4 closed doors...	3/4	true	100	3	210.28	0.000615
sft-cli-run-1788560464997	abstract-03	Recursive Difference Pattern Induction	ARC Challenge	abstract	Polynomial Sequence Induction	Medium	gemini-2.0-flash + openrouter/free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	A mathematical sequence is generated by a cubic polynomial rule: $a_1 = 7, \quad a_2 = 26, \quad a_3 = 63, \quad a_4 = 124, \quad a_5 = 215$ Find the underlying algebraic generating formula $a_n$ and compute the exact value of the 10th term ($a_{10}$). State the exact numerical integer value of $a_{10}$.	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "A mathematical sequence is gen...	1330	true	100	3	300.76	0.000499
sft-cli-run-1788560460592	logic-04	Strict Five-Person Seating Deduction	Formal Logic	logic	Linear Constraint Satisfaction	Hard	qwen/qwq-32b:free + mistralai/mistral-small-24b-instruct-2501:free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	Five colleagues—Evelyn, Frank, Grace, Henry, and Ivy—are seated in a single row of 5 chairs numbered 1 to 5 from left to right. 1. Frank is sitting to the immediate left of Henry. 2. Evelyn is not sitting in chair 1 or chair 5. 3. Grace is sitting immediately adjacent to both Evelyn and Frank. 4. Ivy is sitting in an o...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "Five colleagues—Evelyn, Frank,...	1:Ivy, 2:Evelyn, 3:Grace, 4:Frank, 5:Henry	true	100	3	260.9	0.000574
sft-cli-run-1788560456394	logic-03	The Three Mislabelled Fruit Crates	Formal Logic	logic	Deductive Elimination	Easy	mistralai/mistral-7b-instruct:free + gemini-2.0-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	You are in a warehouse with 3 sealed boxes. One contains only Apples, one contains only Oranges, and one contains a mixture of Apples and Oranges. All three boxes are incorrectly labeled: Box 1 says "Apples", Box 2 says "Oranges", Box 3 says "Apples & Oranges". You are allowed to pick ONE box, reach inside blindly, an...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "You are in a warehouse with 3 ...	The box labeled "Apples & Oranges" (Box 3)	true	100	4	117.25	0.000798
sft-cli-run-1788560451323	logic-02	The Island of Knights, Knaves, and Spies	Formal Logic	logic	Propositional Calculus & Truth Deduction	Hard	deepseek/deepseek-chat:free + gemini-1.5-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	On a remote island, inhabitants are either Knights (who always tell the truth), Knaves (who always lie), or Spies (who can either tell the truth or lie). You meet three people: Alex, Blake, and Casey. You know that exactly one is a Knight, one is a Knave, and one is a Spy. They make the following statements: - Alex sa...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "On a remote island, inhabitant...	Alex: Spy, Blake: Knave, Casey: Knight	true	100	3	245.27	0.000606
sft-cli-run-1788560447200	logic-01	The 3-Jug Decanting Optimization	Formal Logic	logic	State-Space Search & Graph BFS	Medium	mistralai/mistral-7b-instruct:free + meta-llama/llama-3.2-3b-instruct:free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	You have three containers with capacities of 8 liters, 5 liters, and 3 liters. Initially, the 8-liter jug is completely full of water (8, 0, 0), while the 5-liter and 3-liter jugs are empty. There are no markings on the jugs. You can pour water from one jug to another until either the source jug is empty or the destina...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "You have three containers with...	7 steps	true	100	3	317.44	0.000497
sft-cli-run-1788560443188	strategy-01	The 21-Token Subtraction Game (Nim Variant)	Game Theory	strategy	Combinatorial Nim Variants	Easy	qwen/qwen-2.5-72b-instruct:free + mistralai/mistral-small-24b-instruct-2501:free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	Two players play a turn-based mathematical game with a pile of 21 tokens. - On each turn, a player MUST remove either 1, 2, or 3 tokens from the pile. - The player who takes the LAST remaining token wins the entire game. - Player 1 goes first. Both players have perfect information and play with flawless game-theoretic ...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "Two players play a turn-based ...	1 token	true	100	3	277.57	0.00054
sft-cli-run-1788560438847	strategy-03	Pirate Gold Division (5 Rational Pirates)	Game Theory	strategy	Sequential Voting & Backward Induction	Medium	mistralai/mistral-7b-instruct:free + deepseek/deepseek-chat:free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	Five strictly rational, bloodthirsty, and greedy pirates (ranked in seniority: Pirate 1 > Pirate 2 > Pirate 3 > Pirate 4 > Pirate 5) must divide 100 gold coins. The rules: 1. The most senior living pirate proposes a division of the 100 coins. 2. All living pirates (including the proposer) vote on the proposal. 3. If 50...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "Five strictly rational, bloodt...	P1: 98, P2: 0, P3: 1, P4: 0, P5: 1	true	100	3	217.78	0.000632
sft-cli-run-1788560434631	strategy-02	Cournot Duopoly Equilibrium Pricing	Game Theory	strategy	Oligopoly Pricing & Nash Equilibrium	Hard	gemini-2.0-flash + qwen/qwen-2.5-72b-instruct:free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	Two identical competing software firms, Firm A and Firm B, simultaneously choose their output quantities $q_A$ and $q_B$ of an AI API service. The inverse market demand function is given by: $P = 120 - (q_A + q_B)$ Both firms have an identical constant marginal cost of $MC = 12$ per unit and zero fixed costs. Each fir...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "Two identical competing softwa...	qA = 36, qB = 36, Price = $48	true	100	4	114.61	0.000803
sft-cli-run-1788560429596	arc-challenge-02	2D Cellular Lattice Transformation Rule	ARC Challenge	abstract	Inductive Pattern Topology	Hard	mistralai/mistral-7b-instruct:free + gemini-1.5-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	Consider a 3x3 binary grid state that evolves according to a deterministic local rule: Rule: At step $t+1$, cell $(r,c)$ becomes 1 if and only if the sum of its orthogonal Manhattan neighbors (Up, Down, Left, Right) at step $t$ is strictly ODD (1 or 3). Otherwise it becomes 0. Outside borders are strictly 0. Initial s...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "Consider a 3x3 binary grid sta...	0 active cells	true	100	3	247.42	0.000561
sft-cli-run-1788560425317	arc-challenge-01	3x3 Matrix 90-Degree Orthogonal Rotation & Bitwise XOR Merge	ARC Challenge	abstract	Spatial Invariance & Inductive Logic	Medium	openrouter/free + gemini-2.5-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	Given a binary 3x3 input matrix $M$: Row 1: [1, 0, 0] Row 2: [1, 1, 0] Row 3: [0, 0, 1] We perform two consecutive deterministic transformations: 1. Step 1: Rotate matrix $M$ clockwise by $90^\circ$ to produce $M_{\text{rot}}$. 2. Step 2: Compute the element-wise XOR matrix $R = M \oplus M_{\text{rot}}$, where $a \opl...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "Given a binary 3x3 input matri...	6 active bits	true	100	3	287.23	0.000537
sft-cli-run-1788560421274	ifeval-02	Verifiable 20-Word Constrained Summary with Numerical Invariants	IFEval	instruction_following	Exact Word-Count & Structural Invariants	Hard	mistralai/mistral-7b-instruct:free + openrouter/free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	Construct a summary of the dual-agent consensus mechanism that satisfies EVERY one of these 3 rules: 1. The summary text must contain EXACTLY 20 words (counted by whitespace separation). 2. The first word MUST be "Two" and the twentieth (last) word MUST be "truth". 3. The summary MUST mention the exact number "100%" wi...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "Construct a summary of the dua...	Two autonomous neural agents communicate iteratively through multi-turn dialectic consensus until 100% agreement verifies the rigorous mathematical proof of truth	true	100	3	236.84	0.000616
sft-cli-run-1788560417174	ifeval-01	Strict JSON Schema with Negative Word Constraints & Key Counts	IFEval	instruction_following	Constraint Compliance & Schema Enforcement	Medium	gemini-2.5-flash + qwen/qwen-2.5-coder-32b-instruct:free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	You must output a strictly valid JSON object matching ALL of the following 4 constraints: 1. The JSON object must contain EXACTLY three top-level keys: `"status"`, `"agent_count"`, and `"verdict"`. 2. The value of `"status"` must be the string `"SUCCESS"`. 3. The value of `"agent_count"` must be the integer `2`. 4. The...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "You must output a strictly val...	{"status": "SUCCESS", "agent_count": 2, "verdict": "Dual blind logic trials pass"}	true	100	3	214.8	0.000611
sft-cli-run-1788560412930	math-aime-02	Derangements of a 6-Element Permutation Set	MATH / AIME	math	Discrete Combinatorics	Medium	qwen/qwen-2.5-72b-instruct:free + google/gemini-2.0-flash-exp:free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	A derangement $D_n$ (subfactorial $!n$) is a permutation of $n$ elements in which no element appears in its original position. Using the inclusion-exclusion recurrence relation: $$D_n = (n - 1)(D_{n-1} + D_{n-2}), \quad \text{with } D_1 = 0, D_2 = 1$$ Calculate the exact integer value of $D_6$ (the number of derangeme...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "A derangement $D_n$ (subfactor...	265	true	100	3	324.14	0.000516
sft-cli-run-1788560408565	math-aime-01	Least Positive Integer with Triple Modular Congruences	MATH / AIME	math	Number Theory & Chinese Remainder Theorem	Hard	microsoft/phi-3-mini-128k-instruct:free + gemini-2.5-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	Find the least positive integer $X$ satisfying the simultaneous modular system: $$X \equiv 3 \pmod{7}$$ $$X \equiv 4 \pmod{11}$$ $$X \equiv 5 \pmod{13}$$ Compute the unique positive integer $X < 7 \times 11 \times 13 = 1001$. State the exact integer $X$.	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "Find the least positive intege...	927	true	100	3	276.67	0.000594
sft-cli-run-1788560404423	swe-bench-05	scikit-learn Ridge Regression: Gram Matrix Condition Number Squaring	SWE-bench	coding	Numerical Stability & Machine Learning Estimators	Medium	meta-llama/llama-3.2-3b-instruct:free + gemini-2.0-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	In scikit-learn issue scikit-learn__scikit-learn-14201, resolving numerical precision regressions in `Ridge` regression: Given an ill-conditioned design matrix $X \in \mathbb{R}^{n \times p}$ with condition number $\kappa_2(X) = 10^5$: 1. If an estimator solves the normal equations directly via Cholesky decomposition o...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "In scikit-learn issue scikit-l...	Gram Condition Number: 10^10, LAPACK Driver: gelsd	true	100	3	214.98	0.000648
sft-cli-run-1788560400173	swe-bench-04	SymPy Defective Matrix Jordan Block Decomposition & Minimal Polynomial	SWE-bench	coding	Computer Algebra Systems & Symbolic Linear Algebra	Hard	deepseek/deepseek-r1-distill-llama-70b:free + gemini-2.0-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	In SymPy issue sympy__sympy-19453, evaluating `Matrix.jordan_form()` on defective nilpotent and degenerate matrices triggered algebraic infinite recursion. Consider the $3 \times 3$ rational matrix: $$A = \begin{pmatrix} 3 & 1 & 0 \\ 0 & 3 & 1 \\ 0 & 0 & 3 \end{pmatrix}$$ 1. What is the geometric multiplicity $\dim(\ke...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "In SymPy issue sympy__sympy-19...	Geometric Multiplicity: 1, Jordan Block Size: 3x3, Minimal Polynomial: (lambda - 3)^3, (A - 3I)^3: 0 (Zero Matrix)	true	100	4	103.53	0.000992
sft-cli-run-1788560395472	swe-bench-03	Django ORM QuerySet: values() and annotate() GROUP BY Duplication Bug	SWE-bench	coding	ORM Query Compilation & SQL Invariants	Hard	mistralai/mistral-7b-instruct:free + gemini-2.0-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	In a production Django repository (tested under SWE-bench issue django__django-13449 / #31824), an engineer writes the following query to count unique publications per author: ```python Author.objects.values('id').annotate(book_count=Count('books__id', distinct=True)).order_by('pub_date') ``` 1. Because the `Meta.order...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "In a production Django reposit...	Bug: Appends pub_date to GROUP BY clause, Method: order_by()	true	100	3	220.6	0.000664
sft-cli-run-1788560385847	swe-bench-01	Lock-Free Ring Buffer Head-Tail Invariant & Capacity Calculation	SWE-bench	coding	Software Engineering & Concurrency	Medium	meta-llama/llama-3.1-8b-instruct:free + mistralai/mistral-7b-instruct:free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	A high-throughput lock-free Single-Producer Single-Consumer (SPSC) ring buffer of capacity $C = 2^k$ uses atomic 64-bit integer monotonically increasing sequence counters: `head` (written by consumer) and `tail` (written by producer). The buffer indexing uses bitwise masking: `index = sequence & (C - 1)`. 1. If $C = 1...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "A high-throughput lock-free Si...	Mask = 0x3FF, Full = (tail - head == 1024), Count = 700 items	true	100	4	93.44	0.000864
sft-cli-run-1788560380337	gpqa-diamond-05	Crick Wobble Hypothesis Inosine Base Pairing & tRNA Synthetase Universality	GPQA Diamond	science	Molecular Genetics & Translation Wobble	Hard	meta-llama/llama-3.2-3b-instruct:free + gemini-2.0-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	In standard biological translation across living organisms: 1. In Francis Crick's classic Wobble Hypothesis, post-transcriptional deamination of adenosine at the first (5') anticodon position produces the non-canonical modified nucleoside Inosine (I). What are ALL three mRNA 3'-codon bases that Inosine in the wobble po...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "In standard biological transla...	Wobble Bases: A, U, C, Synthetases: 20	true	100	3	242.07	0.00062
sft-cli-run-1788560376224	gpqa-diamond-04	Compton Relativistic Scattering Wavelength Shift at 90-Degree Deflection	GPQA Diamond	science	Quantum Electrodynamics & Compton Scattering	Hard	deepseek/deepseek-chat:free + gemini-2.0-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	A high-energy gamma photon with initial incident wavelength $\lambda = 0.500\text{ pm}$ ($5.00 \times 10^{-13}\text{ m}$) undergoes Compton scattering against an initially stationary free electron ($m_e = 9.109 \times 10^{-31}\text{ kg}$). The scattered photon emerges at a scattering angle of $\theta = 90.0^\circ$ rela...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "A high-energy gamma photon wit...	lambda = 2.926 pm, Energy Fraction = 0.829	true	100	3	211.45	0.000692
sft-cli-run-1788560367899	gpqa-diamond-02	Competitive Enzyme Inhibition Apparent Km Ratio	GPQA Diamond	science	Biochemistry & Michaelis-Menten Kinetics	Hard	meta-llama/llama-3.2-3b-instruct:free + gemini-1.5-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	An enzyme follows standard Michaelis-Menten kinetics with substrate $S$, having an uninhibited Michaelis constant $K_m = 4.0\text{ \mu M}$ and $V_{\text{max}} = 100\text{ \mu M/s}$. A competitive inhibitor $I$ with dissociation constant $K_i = 2.0\text{ \mu M}$ is added at a concentration $[I] = 6.0\text{ \mu M}$. In ...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "An enzyme follows standard Mic...	Km_app = 16 μM, v = 50 μM/s	true	100	4	116.66	0.000867
sft-cli-run-1788560363111	gpqa-diamond-01	3D Isotropic Quantum Harmonic Oscillator Degeneracy	GPQA Diamond	science	Quantum Mechanics & Degeneracy	Extreme	cognitivecomputations/dolphin3.0-r1-mistral-24b:free + gemini-1.5-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	Consider a particle of mass $m$ trapped in a three-dimensional isotropic quantum harmonic oscillator potential $V(r) = \frac{1}{2} m \omega^2 (x^2 + y^2 + z^2)$. The total energy eigenvalues are quantized according to: $$E_n = \hbar \omega \left(n + \frac{3}{2}\right), \quad n = n_x + n_y + n_z \in \{0, 1, 2, 3, \dots\...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "Consider a particle of mass $m...	21 states	true	100	3	281.81	0.000549
sft-cli-run-1788560359040	mmlu-pro-02	Byzantine Agreement Quorum Intersection Invariant	MMLU-Pro	science	Distributed Systems & Byzantine Fault Tolerance	Medium	deepseek/deepseek-r1-distill-llama-70b:free + microsoft/phi-3-mini-128k-instruct:free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	In a distributed consensus network running the classical PBFT (Practical Byzantine Fault Tolerance) protocol with $N$ total replica nodes, up to $f$ nodes may be Byzantine (arbitrarily malicious, colluding, or crashing). For the protocol to maintain safety (no two non-faulty nodes commit conflicting values) and livenes...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "In a distributed consensus net...	13 nodes	true	100	3	281.8	0.000541
sft-cli-run-1788560354942	mmlu-pro-01	Relativistic Carnot Engine Efficiency with Heat Exchange	MMLU-Pro	science	Physics & Thermodynamics	Hard	deepseek/deepseek-chat:free + mistralai/mistral-small-24b-instruct-2501:free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	A hypothetical relativistic heat engine operates between two thermal reservoirs with temperatures $T_H = 1200\text{ K}$ and $T_C = 300\text{ K}$. During each cycle, the working fluid absorbs $Q_H = 4800\text{ J}$ of heat from the hot reservoir. Due to finite-time heat transfer kinetics across the boundary thermal condu...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "A hypothetical relativistic he...	Efficiency = 50%, Work = 2400 J	true	100	3	233.17	0.000594
sft-cli-run-1788560345957	frontiermath-03	Ramanujan Expander Graph Alon-Boppana Bound & Second Eigenvalue	FrontierMath	math	Spectral Graph Theory & Expander Graphs	Hard	qwen/qwen-2.5-72b-instruct:free + openrouter/free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	Let $G$ be an infinite family of connected $d$-regular graphs with adjacency eigenvalues $d = \lambda_1 > \lambda_2 \ge \dots \ge \lambda_n \ge -d$. 1. According to the Alon-Boppana theorem, for any $\epsilon > 0$, as $n \to \infty$, the second largest eigenvalue satisfies $\lambda_2 \ge 2\sqrt{d - 1} - \epsilon$. A $d...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "Let $G$ be an infinite family ...	Bound: 6, Spectral Gap: 4	true	100	3	245.91	0.000578
sft-cli-run-1788560341802	frontiermath-02	Ruzsa-Szemerédi Triangle Removal Lemma & Behrend 3-AP Density	FrontierMath	math	Extremal Graph Theory & Removal Lemmas	Extreme	gemini-2.5-flash + mistralai/mistral-7b-instruct:free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	The Ruzsa-Szemerédi Triangle Removal Lemma states that any graph on $n$ vertices with at most $\delta(\epsilon) n^3$ triangles can be made triangle-free by removing at most $\epsilon n^2$ edges. To prove that $\delta(\epsilon)^{-1}$ cannot be polynomial in $1/\epsilon$, Ruzsa and Szemerédi constructed graphs from large...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "The Ruzsa-Szemerédi Triangle R...	Exponent: 1/2	true	100	3	251.72	0.000588
sft-cli-run-1788560337761	frontiermath-01	Congruent Number Elliptic Curve Mordell-Weil Torsion & 2-Selmer Rank	FrontierMath	math	Arithmetic Geometry & Elliptic Curves	Extreme	qwen/qwen-2.5-72b-instruct:free + gemini-2.0-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	Consider the family of congruent number elliptic curves defined over $\mathbb{Q}$ by: $$E_d: y^2 = x^3 - d^2 x$$ where $d$ is a square-free positive integer. By the Mordell-Weil theorem, the group of rational points is finitely generated: $E_d(\mathbb{Q}) \cong \mathbb{Z}^r \oplus E_d(\mathbb{Q})_{\text{tors}}$. 1. Wha...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "Consider the family of congrue...	Torsion Group: Z/2Z x Z/2Z (order 4), Rank r: 1	true	100	3	221.73	0.000651
sft-cli-run-1788560333633	hle-04	Ramsey Commitment vs Discretion at the Zero Lower Bound (ZLB)	Humanity's Last Exam	science	Frontier Quantitative Macroeconomics & Ramsey Policy	Hard	microsoft/phi-3-mini-128k-instruct:free + google/gemini-2.0-flash-exp:free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	In modern New Keynesian monetary theory under a binding Zero Lower Bound (ZLB) on the nominal interest rate: 1. Does a central bank operating under full Ramsey commitment keep the nominal interest rate at zero for a longer duration than a discretionary central bank once the crisis natural rate shock has subsided (the c...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "In modern New Keynesian moneta...	Lower For Longer: Yes, Channel: Lower Real Rate	true	100	3	225.45	0.000675
sft-cli-run-1788560329616	hle-03	Kitaev Quantum Local Hamiltonian Theorem & QMA Completeness	Humanity's Last Exam	science	Quantum Complexity Theory & Hamiltonian Verification	Hard	gemini-2.5-flash + openrouter/free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	In quantum computational complexity theory: 1. According to the foundational Kitaev Local Hamiltonian Theorem (Kitaev-Shen-Vyalyi), deciding whether the ground-state energy $E_0$ of a $k$-local Hamiltonian on $n$ qubits is $\le a$ versus $\ge b$ (with promised spectral promise gap $b - a \ge 1/\text{poly}(n)$) is compl...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "In quantum computational compl...	Complexity Class: QMA, Minimum Locality k: 2	true	100	3	244.21	0.000619
sft-cli-run-1788560325557	hle-02	TKNN Invariant First Chern Number and Quantized Hall Conductance	Humanity's Last Exam	science	Topological Quantum Matter & Chern Numbers	Extreme	qwen/qwq-32b:free + gemini-1.5-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	In the integer quantum Hall effect (Thouless-Kohmoto-Nightingale-den Nijs / TKNN formulation), the quantized Hall conductance $\sigma_{xy}$ of an isolated 2D electron gas on a periodic lattice torus is governed by the topological first Chern number $C_1 \in \mathbb{Z}$: $$\sigma_{xy} = C_1 \frac{e^2}{h}, \quad C_1 = \f...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "In the integer quantum Hall ef...	Chern Number: 1, Hall Conductance: 1 e^2/h	true	100	3	202.08	0.000692
sft-cli-run-1788560321175	hle-01	CRISPR-Cas9 NHEJ Indel Out-of-Frame Frameshift Probability	Humanity's Last Exam	science	Molecular Biology & CRISPR Repair Dynamics	Extreme	openrouter/free + mistralai/mistral-small-24b-instruct-2501:free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	In targeted genome editing, SpCas9 generates a double-strand break (DSB) 3 base pairs upstream of the NGG PAM sequence within a protein-coding exon. Repair proceeds predominantly via Non-Homologous End Joining (NHEJ) resulting in small insertions or deletions (indels). Assuming an idealized uniform prior distribution a...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "In targeted genome editing, Sp...	Frameshift Probability = 2/3, MMEJ Modulo Class = 2	true	100	3	215.53	0.00066
sft-cli-run-1788560316926	abstract-04	The Monty Hall Variant with 4 Doors and 2 Car Prizes	Game Theory	strategy	Bayesian Probability & Counterfactual Switching	Hard	qwen/qwen-2.5-72b-instruct:free + gemini-2.5-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	A game show has 4 closed doors. Behind 2 of the doors are brand-new Luxury Cars, and behind the other 2 doors are Goats. All distributions are equally likely. 1. The contestant picks Door #1. 2. The host, who knows what is behind every door, opens ONE of the remaining doors (Door #2, #3, or #4) that contains a Goat. 3...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "A game show has 4 closed doors...	3/4	true	100	3	258.14	0.000615
sft-cli-run-1788560312919	abstract-03	Recursive Difference Pattern Induction	ARC Challenge	abstract	Polynomial Sequence Induction	Medium	openrouter/free + qwen/qwen-2.5-72b-instruct:free	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	A mathematical sequence is generated by a cubic polynomial rule: $a_1 = 7, \quad a_2 = 26, \quad a_3 = 63, \quad a_4 = 124, \quad a_5 = 215$ Find the underlying algebraic generating formula $a_n$ and compute the exact value of the 10th term ($a_{10}$). State the exact numerical integer value of $a_{10}$.	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "A mathematical sequence is gen...	1330	true	100	3	333.69	0.000497
sft-cli-run-1788560308817	logic-04	Strict Five-Person Seating Deduction	Formal Logic	logic	Linear Constraint Satisfaction	Hard	qwen/qwen-2.5-coder-32b-instruct:free + gemini-2.0-flash	You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement.	Five colleagues—Evelyn, Frank, Grace, Henry, and Ivy—are seated in a single row of 5 chairs numbered 1 to 5 from left to right. 1. Frank is sitting to the immediate left of Henry. 2. Evelyn is not sitting in chair 1 or chair 5. 3. Grace is sitting immediately adjacent to both Evelyn and Frank. 4. Ivy is sitting in an o...	[ { "role": "system", "content": "You are a frontier reasoning model trained via multi-agent double-blind consensus. Solve with strict mathematical, scientific, and algorithmic rigor. Conclude with a bold FINAL ANSWER: statement." }, { "role": "user", "content": "Five colleagues—Evelyn, Frank,...	1:Ivy, 2:Evelyn, 3:Grace, 4:Frank, 5:Henry	true	100	3	268.43	0.000573

End of preview. Expand in Data Studio

GlimmaryKarl/DualBlind

Curated Frontier Reasoning and Direct Preference Optimization (DPO) Dataset Generated from Double-Blind Multi-Agent Arena Evaluations.

This dataset was generated using the DualBlind AI Benchmark Arena. In this setup, two independent frontier AI models engage in multi-turn double-blind dialogue to solve extreme-difficulty benchmark problems, verifying their peer's proofs, raising counter-examples, and reaching mathematical consensus.

Dataset Structure & Strict Quality Gate

Strict 100% Accuracy Quality Gate (Active): Only trials that achieved 100% automated verification against canonical ground-truth solutions are admitted into GlimmaryKarl/DualBlind. Incomplete trials, partial solutions (<100%), and unverified outputs are strictly blocked from entry.

Total Arena Trials Evaluated: 2254
Verified 100% Accurate Trials Admitted: 1971 (87.4% pass rate)
Ineligible Trials Filtered Out (<100% or Refuted): 283
Quality Gate Policy: Zero-tolerance for unverified or imperfect conjectures. Every single sample provides a mathematically and algorithmically verified canonical solution.

Subsets:

sft_reasoning (1502 samples): Supervised Fine-Tuning records containing high-density step-by-step chain-of-thought reasoning traces culminating in 100% verified ground-truth solutions.
dpo_preferences (1501 pairs): Direct Preference Optimization pairs (prompt, chosen, rejected) pairing the 100% verified consensus proof as chosen against flawed peer conjectures or refuted hypotheses as rejected.

Benchmark Suites Covered

GPQA Diamond: 248 runs
MMLU-Pro: 186 runs
Humanity's Last Exam: 112 runs
Game Theory: 313 runs
ARC Challenge: 253 runs
Formal Logic: 229 runs
IFEval: 166 runs
MATH / AIME: 98 runs
SWE-bench: 245 runs
FrontierMath: 98 runs
General Benchmark: 23 runs

Models Represented

gemini-2.5-flash
openrouter/free
deepseek/deepseek-r1-distill-llama-70b:free
cognitivecomputations/dolphin3.0-r1-mistral-24b:free
meta-llama/llama-3.1-8b-instruct:free
gemini-2.0-flash
gemini-3.7-flash
gemini-1.5-flash
deepseek/deepseek-r1:free
qwen/qwq-32b:free
mistralai/mistral-small-24b-instruct-2501:free
mistralai/mistral-7b-instruct:free
deepseek/deepseek-chat:free
meta-llama/llama-3.2-3b-instruct:free
qwen/qwen-2.5-72b-instruct:free
qwen/qwen-2.5-coder-32b-instruct:free
google/gemini-2.0-flash-exp:free
microsoft/phi-3-mini-128k-instruct:free
meta-llama/llama-3.3-70b-instruct:free
google/gemma-2-9b-it:free
nvidia/llama-3.1-nemotron-70b-instruct:free
poolside/laguna-s-2.1:free
poolside/laguna-xs-2.1:free
openai/gpt-3.5-turbo
thedrummer/skyfall-36b-v2
liquid/lfm-2.5-2.6b:free
google/gemma-4-26b-a4b-it:free
minimax/minimax-m3:free
z-ai/glm-4.7-flash
tencent/hy-mt2-30b-a3b
openai/gpt-4o-mini
meta-llama/llama-3.3-70b-instruct
qwen/qwen-2.5-72b-instruct
meta/muse-glimmer-30b
google-gemini-3.7-flash
claude-3-7-sonnet-20250219
deepseek-r1
o3-mini
gpt-4.5-preview
ox-alpha
nvidia/nemotron-3-nano
amazon/nova-lite-v1
meta-llama/llama-3.1-70b-instruct
deepseek-deepseek-v3
anthropic-claude-3-haiku
gpt-4o

Usage with Hugging Face Datasets

from datasets import load_dataset

# Load SFT Reasoning split
sft_ds = load_dataset("GlimmaryKarl/DualBlind", "sft_reasoning", split="train")
print(sft_ds[0]["messages"])

# Load DPO Preference split
dpo_ds = load_dataset("GlimmaryKarl/DualBlind", "dpo_preferences", split="train")
print(dpo_ds[0]["chosen"])
print(dpo_ds[0]["rejected"])

100% Free Fine-Tuning Guide (Unsloth on Google Colab T4)

You can fine-tune Llama-3.1-8B-Instruct or Qwen-2.5-7B in ~25 minutes on a free Google Colab T4 GPU:

pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
pip install --no-deps trl peft accelerate bitsandbytes

from unsloth import FastLanguageModel
from trl import SFTTrainer
from transformers import TrainingArguments
from datasets import load_dataset

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="unsloth/Llama-3.1-8B-Instruct",
    max_seq_length=2048,
    load_in_4bit=True,
)

model = FastLanguageModel.get_peft_model(
    model,
    r=16,
    target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
    lora_alpha=16,
    lora_dropout=0,
    bias="none",
)

dataset = load_dataset("GlimmaryKarl/DualBlind", "sft_reasoning", split="train")

trainer = SFTTrainer(
    model=model,
    train_dataset=dataset,
    dataset_text_field="text",
    max_seq_length=2048,
    tokenizer=tokenizer,
    args=TrainingArguments(
        per_device_train_batch_size=2,
        gradient_accumulation_steps=4,
        warmup_steps=5,
        max_steps=60,
        learning_rate=2e-4,
        fp16=True,
        logging_steps=1,
        output_dir="outputs",
    ),
)
trainer.train()

License

Apache 2.0. Free for commercial, research, and educational use.

Downloads last month: 60