Update README.md

README.md

@@ -16,10 +16,21 @@ Deployment-ready model artifacts for the AIMO Proof Pilot submission. Every subf
 `Olmo3SinkForCausalLM` (olmo3_sink, DeepSeek-V4-Flash transplanted tokenizer, vocab 129,280)
 family member and they share one tokenizer.
 
+> **Training cutoff — no IMO 2026 contamination.** Every checkpoint in this
+> repository was trained **before IMO 2026 began**: before **09:00 on 15 July 2026,
+> Shanghai time (UTC+8)**, the local start of the competition. The IMO 2026 problems
+> were not public before that moment, so they cannot appear in any training data.
+
+| Benchmark | Result | Grader | Setting | Solutions |
+|---|---|---|---|---|
+| **IMO 2026** | **19 / 42 — Bronze medal** | [Human expert (ex-IMO)](https://github.com/fieldsmodelorg/AIMO-Proof-Pilot/tree/main/imo_2026_eval) | `high` budget | [solutions.csv](https://github.com/fieldsmodelorg/AIMO-Proof-Pilot/blob/main/imo_2026_eval/raw/imo2026-deploy-budget-high-tournament_submission.csv) |
+
+
 Related repositories: [code](https://github.com/ycchen-tw/proof-pilot-codes) ·
 [intermediate checkpoints](https://huggingface.co/ycchen/proof-pilot-checkpoints) ·
 [training-data artifacts](https://huggingface.co/datasets/ycchen/proof-pilot-datasets).
 
+
 | Subfolder | Model | Notes |
 |---|---|---|
 | `soft-distill-7b-deploy/` | stage1-v2-7b soft-distill v2 (deploy) | 7B off-policy soft distillation (bf16), with tokenizer + chat template |