opencompass/.github/scripts/oc_score_baseline_testrange.yaml

chat:
    glm-4-9b-chat-hf:
        gsm8k_accuracy: 56.25
        race-high_accuracy: 84.38
    glm-4-9b-chat-turbomind:
        gsm8k_accuracy: 71.88
        race-high_accuracy: 90.62
    glm-4-9b-chat-vllm:
        gsm8k_accuracy: 65.62
        race-high_accuracy: 90.62
    deepseek-7b-chat-hf:
        gsm8k_accuracy: 46.88
        race-high_accuracy: 81.25
    deepseek-r1-distill-llama-8b-turbomind:
        gsm8k_accuracy: 34.38
        race-high_accuracy: 81.25
    deepseek-r1-distill-qwen-1_5b-turbomind:
        gsm8k_accuracy: 28.12
        race-high_accuracy: 53.12
    deepseek-7b-chat-vllm:
        gsm8k_accuracy: 50
        race-high_accuracy: 78.12
    gemma2-2b-it-hf:
        gsm8k_accuracy: 50
        race-high_accuracy: 75
    gemma2-9b-it-hf:
        gsm8k_accuracy: 68.75
        race-high_accuracy: 84.38
    gemma-2b-it-hf:
        gsm8k_accuracy: 3.12
        race-high_accuracy: 40.62
    gemma-7b-it-hf:
        gsm8k_accuracy: 40.62
        race-high_accuracy: 68.75
    gemma-2-9b-it-turbomind:
        gsm8k_accuracy: 68.75
        race-high_accuracy: 84.38
    gemma-2-27b-it-turbomind:
        gsm8k_accuracy: 78.12
        race-high_accuracy: 93.75
    gemma-7b-it-vllm:
        gsm8k_accuracy: 46.88
        race-high_accuracy: 68.75
    internlm2_5-7b-chat-hf:
        gsm8k_accuracy: 84.38
        race-high_accuracy: 90.62
    internlm3-8b-instruct-hf:
        gsm8k_accuracy: 65.62
        race-high_accuracy: 87.5
    internlm2_5-7b-chat-turbomind:
        gsm8k_accuracy: 81.25
        race-high_accuracy: 90.62
    internlm2-chat-1.8b-turbomind:
        gsm8k_accuracy: 25.00
        race-high_accuracy: 84.38
    internlm2-chat-1.8b-sft-turbomind:
        gsm8k_accuracy: 34.38
        race-high_accuracy: 84.38
    internlm2-chat-7b-lmdeploy:
        gsm8k_accuracy: 59.38
        race-high_accuracy: 87.50
    internlm2-chat-7b-sft-turbomind:
        gsm8k_accuracy: 56.25
        race-high_accuracy: 87.50
    internlm3-8b-instruct-turbomind:
        gsm8k_accuracy: 65.62
        race-high_accuracy: 87.5
    internlm2-chat-7b-vllm:
        gsm8k_accuracy: 43.75
        race-high_accuracy: 84.38
    llama-3_1-8b-instruct-hf:
        gsm8k_accuracy: 84.38
        race-high_accuracy: 90.62
    llama-3_2-3b-instruct-hf:
        gsm8k_accuracy: 68.75
        race-high_accuracy: 81.25
    llama-3-8b-instruct-hf:
        gsm8k_accuracy: 68.75
        race-high_accuracy: 87.5
    llama-2-7b-chat-turbomind:
        gsm8k_accuracy: 18.75
        race-high_accuracy: 46.88
    llama-3_1-8b-instruct-turbomind:
        gsm8k_accuracy: 84.38
        race-high_accuracy: 90.62
    llama-3_2-3b-instruct-turbomind:
        gsm8k_accuracy: 65.62
        race-high_accuracy: 81.25
    llama-3-8b-instruct-turbomind:
        gsm8k_accuracy: 65.62
        race-high_accuracy: 84.38
    mistral-7b-instruct-v0.2-hf:
        gsm8k_accuracy: 40.62
        race-high_accuracy: 75
    mistral-7b-instruct-v0.3-hf:
        gsm8k_accuracy: 40.62
        race-high_accuracy: 75
    mistral-nemo-instruct-2407-hf:
        gsm8k_accuracy: 75
        race-high_accuracy: 81.25
    mistral-nemo-instruct-2407-turbomind:
        gsm8k_accuracy: 71.88
        race-high_accuracy: 75
    mistral-7b-instruct-v0.1-vllm:
        gsm8k_accuracy: 34.38
        race-high_accuracy: 68.75
    mistral-7b-instruct-v0.2-vllm:
        gsm8k_accuracy: 31.25
        race-high_accuracy: 75.00
    qwen2.5-0.5b-instruct-hf:
        gsm8k_accuracy: 34.38
        race-high_accuracy: 46.88
    qwen2.5-3b-instruct-hf :
        gsm8k_accuracy: 53.12
        race-high_accuracy: 90.62
    qwen2.5-0.5b-instruct-turbomind:
        gsm8k_accuracy: 28.12
        race-high_accuracy: 43.75
    qwen2.5-3b-instruct-turbomind:
        gsm8k_accuracy: 56.25
        race-high_accuracy: 90.62
    qwen1.5-0.5b-chat-hf:
        gsm8k_accuracy: 0
        race-high_accuracy: 53.12
    qwen2-1.5b-instruct-hf:
        gsm8k_accuracy: 62.5
        race-high_accuracy: 84.38
    qwen2-7b-instruct-hf:
        gsm8k_accuracy: 68.75
        race-high_accuracy: 90.62
    qwen2-1.5b-instruct-turbomind:
        gsm8k_accuracy: 56.25
        race-high_accuracy: 84.38
    qwen2-7b-instruct-turbomind:
        gsm8k_accuracy: 75.00
        race-high_accuracy: 87.50
    qwen1.5-0.5b-chat-vllm:
        gsm8k_accuracy: 3.12
        race-high_accuracy: 53.12
    yi-1.5-6b-chat-hf:
        gsm8k_accuracy: 65.62
        race-high_accuracy: 84.38
    yi-1.5-9b-chat-hf:
        gsm8k_accuracy: 75
        race-high_accuracy: 93.75
    yi-1.5-6b-chat-turbomind:
        gsm8k_accuracy: 59.38
        race-high_accuracy: 84.38
    yi-1.5-9b-chat-turbomind:
        gsm8k_accuracy: 78.12
        race-high_accuracy: 93.75
    deepseek-v2_lite-chat-turbomind:
        gsm8k_accuracy: 37.50
        race-high_accuracy: 71.88
    gemma2-27b-it-hf:
        gsm8k_accuracy: 71.88
        race-high_accuracy: 93.75
    internlm2_5-20b-chat-hf:
        gsm8k_accuracy: 84.38
        race-high_accuracy: 87.5
    internlm2_5-20b-chat-turbomind:
        gsm8k_accuracy: 87.50
        race-high_accuracy: 87.5
    mistral-small-instruct-2409-hf:
        gsm8k_accuracy: 81.25
        race-high_accuracy: 87.50
    mistral-small-instruct-2409-turbomind:
        gsm8k_accuracy: 78.12
        race-high_accuracy: 87.50
    phi-4:
        gsm8k_accuracy: 81.25
        race-high_accuracy: 87.50
    qwen2.5-14b-instruct-hf:
        gsm8k_accuracy: 71.88
        race-high_accuracy: 96.88
    qwen2.5-14b-instruct-turbomind:
        gsm8k_accuracy: 71.88
        race-high_accuracy: 96.88
    yi-1.5-34b-chat-turbomind:
        gsm8k_accuracy: 71.88
        race-high_accuracy: 93.75
    deepseek-67b-chat-turbomind:
        gsm8k_accuracy: 71.88
        race-high_accuracy: 75.00
    deepseek-r1-distill-qwen-32b-turbomind:
        gsm8k_accuracy: 31.25
        race-high_accuracy: 90.62
    llama-3_3-70b-instruct-turbomind:
        gsm8k_accuracy: 93.75
        race-high_accuracy: 87.5
    mixtral-large-instruct-2411-turbomind:
        gsm8k_accuracy: 87.50
        race-high_accuracy: 93.75
    nvidia-3_1-Nemotron-70b-instruct-HF-turbomind:
        gsm8k_accuracy: 90.62
        race-high_accuracy: 53.12
    qwen2.5-72b-instruct-turbomind:
        gsm8k_accuracy: 78.12
        race-high_accuracy: 90.62
    deepseek-r1-distill-llama-70b-turbomind:
        gsm8k_accuracy: 50.00
        race-high_accuracy: 87.50
    deepseek-v2_5-1210-turbomind:
        gsm8k_accuracy: 90.62
        race-high_accuracy: 84.38
    mixtral-8x22b-instruct-v0.1-turbomind:
        gsm8k_accuracy: 71.88
        race-high_accuracy: 78.12
base:
    glm-4-9b-turbomind:
        gsm8k_accuracy: 59.38
        GPQA_diamond_accuracy: 28.12
        race-high_accuracy: 93.75
        winogrande_accuracy: 84.38
    deepseek-7b-base-hf:
        gsm8k_accuracy: 25
        GPQA_diamond_accuracy: 0
        race-high_accuracy: 46.88
        winogrande_accuracy: 71.88
    deepseek-7b-base-turbomind:
        gsm8k_accuracy: 18.75
        GPQA_diamond_accuracy: 3.12
        race-high_accuracy: 50.00
        winogrande_accuracy: 84.38
    deepseek-moe-16b-base-vllm:
        gsm8k_accuracy: 21.88
        GPQA_diamond_accuracy: 0
        race-high_accuracy: 25
        winogrande_accuracy: 68.75
    gemma2-2b-hf:
        gsm8k_accuracy: 31.25
        GPQA_diamond_accuracy: 3.12
        race-high_accuracy: 56.25
        winogrande_accuracy: 75.00
    gemma2-9b-hf:
        gsm8k_accuracy: 75.00
        GPQA_diamond_accuracy: 0
        race-high_accuracy: 84.38
        winogrande_accuracy: 81.25
    gemma-2b-hf:
        gsm8k_accuracy: 21.88
        GPQA_diamond_accuracy: 3.12
        race-high_accuracy: 21.88
        winogrande_accuracy: 53.12
    gemma-7b-hf:
        gsm8k_accuracy: 56.25
        GPQA_diamond_accuracy: 3.12
        race-high_accuracy: 65.62
        winogrande_accuracy: 71.88
    gemma-2-9b-turbomind:
        gsm8k_accuracy: 68.75
        GPQA_diamond_accuracy: 0
        race-high_accuracy: 84.38
        winogrande_accuracy: 81.25
    gemma-2b-vllm:
        gsm8k_accuracy: 15.62
        GPQA_diamond_accuracy: 3.12
        race-high_accuracy: 28.12
        winogrande_accuracy: 68.75
    gemma-7b-vllm:
        gsm8k_accuracy: 53.12
        GPQA_diamond_accuracy: 6.25
        race-high_accuracy: 81.25
        winogrande_accuracy: 81.25
    internlm2_5-7b-hf:
        gsm8k_accuracy: 37.5
        GPQA_diamond_accuracy: 25
        race-high_accuracy: 93.75
        winogrande_accuracy: 71.88
    internlm2-7b-hf:
        gsm8k_accuracy: 53.12
        GPQA_diamond_accuracy: 18.75
        race-high_accuracy: 62.5
        winogrande_accuracy: 78.12
    internlm2-1.8b-turbomind:
        gsm8k_accuracy: 12.50
        GPQA_diamond_accuracy: 9.38
        race-high_accuracy: 71.88
        winogrande_accuracy: 75
    internlm2_5-7b-turbomind:
        gsm8k_accuracy: 62.5
        GPQA_diamond_accuracy: 31.25
        race-high_accuracy: 93.75
        winogrande_accuracy: 87.5
    internlm2-7b-turbomind:
        gsm8k_accuracy: 53.12
        GPQA_diamond_accuracy: 25.00
        race-high_accuracy: 78.12
        winogrande_accuracy: 71.88
    internlm2-base-7b-turbomind:
        gsm8k_accuracy: 25.00
        GPQA_diamond_accuracy: 34.38
        race-high_accuracy: 71.88
        winogrande_accuracy: 62.50
    llama-2-7b-hf:
        gsm8k_accuracy: 21.88
        GPQA_diamond_accuracy: 21.88
        race-high_accuracy: 40.62
        winogrande_accuracy: 71.88
    llama-3_1-8b-hf:
        gsm8k_accuracy: 78.12
        GPQA_diamond_accuracy: 25
        race-high_accuracy: 90.62
        winogrande_accuracy: 62.5
    llama-3-8b-hf:
        gsm8k_accuracy: 46.88
        GPQA_diamond_accuracy: 6.25
        race-high_accuracy: 65.62
        winogrande_accuracy: 65.62
    llama-3.1-8b-turbomind:
        gsm8k_accuracy: 56.25
        GPQA_diamond_accuracy: 9.38
        race-high_accuracy: 78.12
        winogrande_accuracy: 78.12
    llama-3-8b-turbomind:
        gsm8k_accuracy: 46.88
        GPQA_diamond_accuracy: 12.50
        race-high_accuracy: 65.62
        winogrande_accuracy: 81.25
    mistral-7b-v0.3-hf:
        gsm8k_accuracy: 31.25
        GPQA_diamond_accuracy: 6.25
        race-high_accuracy: 62.5
        winogrande_accuracy: 59.38
    qwen2.5-7b-hf:
        gsm8k_accuracy: 81.25
        GPQA_diamond_accuracy: 18.75
        race-high_accuracy: 87.5
        winogrande_accuracy: 71.88
    qwen2.5-1.5b-turbomind:
        gsm8k_accuracy: 59.38
        GPQA_diamond_accuracy: 21.88
        race-high_accuracy: 78.12
        winogrande_accuracy: 71.88
    qwen2.5-7b-turbomind:
        gsm8k_accuracy: 78.12
        GPQA_diamond_accuracy: 21.88
        race-high_accuracy: 87.5
        winogrande_accuracy: 75.00
    qwen1.5-moe-a2.7b-hf:
        gsm8k_accuracy: 62.5
        GPQA_diamond_accuracy: 18.75
        race-high_accuracy: 84.38
        winogrande_accuracy: 75
    qwen2-0.5b-hf:
        gsm8k_accuracy: 25
        GPQA_diamond_accuracy: 0
        race-high_accuracy: 40.62
        winogrande_accuracy: 62.5
    qwen2-1.5b-hf:
        gsm8k_accuracy: 59.38
        GPQA_diamond_accuracy: 9.38
        race-high_accuracy: 81.25
        winogrande_accuracy: 62.5
    qwen2-7b-hf:
        gsm8k_accuracy: 68.75
        GPQA_diamond_accuracy: 9.38
        race-high_accuracy: 87.5
        winogrande_accuracy: 68.75
    qwen2-1.5b-turbomind:
        gsm8k_accuracy: 56.25
        GPQA_diamond_accuracy: 12.50
        race-high_accuracy: 81.25
        winogrande_accuracy: 75
    qwen2-7b-turbomind:
        gsm8k_accuracy: 65.62
        GPQA_diamond_accuracy: 12.5
        race-high_accuracy: 87.5
        winogrande_accuracy: 75
    qwen1.5-0.5b-vllm:
        gsm8k_accuracy: 9.38
        GPQA_diamond_accuracy: 0
        race-high_accuracy: 56.25
        winogrande_accuracy: 62.50
    yi-1.5-6b-hf:
        gsm8k_accuracy: 62.5
        GPQA_diamond_accuracy: 3.12
        race-high_accuracy: 87.5
        winogrande_accuracy: 62.5
    yi-1.5-9b-hf:
        gsm8k_accuracy: 75
        GPQA_diamond_accuracy: 40.62
        race-high_accuracy: 87.5
        winogrande_accuracy: 59.38
    yi-1.5-9b-turbomind:
        gsm8k_accuracy: 75.00
        GPQA_diamond_accuracy: 40.62
        race-high_accuracy: 87.5
        winogrande_accuracy: 65.62
    internlm2-20b-turbomind:
        gsm8k_accuracy: 71.88
        GPQA_diamond_accuracy: 18.75
        race-high_accuracy: 68.75
        winogrande_accuracy: 81.25
    qwen2.5-14b-hf:
        gsm8k_accuracy: 75
        GPQA_diamond_accuracy: 37.5
        race-high_accuracy: 93.75
        winogrande_accuracy: 84.38
    qwen2.5-32b-hf:
        gsm8k_accuracy: 87.5
        GPQA_diamond_accuracy: 31.25
        race-high_accuracy: 93.75
        winogrande_accuracy: 78.12
    qwen2.5-32b-turbomind:
        gsm8k_accuracy: 90.62
        GPQA_diamond_accuracy: 31.25
        race-high_accuracy: 93.75
        winogrande_accuracy: 81.25
    deepseek-67b-base-turbomind:
        gsm8k_accuracy: 62.50
        GPQA_diamond_accuracy: 31.25
        race-high_accuracy: 78.12
        winogrande_accuracy: 81.25
    llama-3-70b-turbomind:
        gsm8k_accuracy: 56.25
        GPQA_diamond_accuracy: 15.62
        race-high_accuracy: 93.75
        winogrande_accuracy: 84.38
    qwen2.5-72b-turbomind:
        gsm8k_accuracy: 84.38
        GPQA_diamond_accuracy: 40.62
        race-high_accuracy: 93.75
        winogrande_accuracy: 87.5
    deepseek-v2-turbomind:
        gsm8k_accuracy: 65.62
        GPQA_diamond_accuracy: 3.12
        race-high_accuracy: 93.75
        winogrande_accuracy: 81.25