jiangzhs/OpenCompass
1
0
Fork 0
mirror of https://github.com/open-compass/opencompass.git synced 2025-05-30 16:03:24 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
zhulinJulia24 2025-05-13 10:45:13 +08:00
parent 3472ed113d
commit 6dbbd80af0
1 changed files with 63 additions and 63 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

126
.github/scripts/oc_score_baseline_testrange.yaml vendored
View File

@ -18,7 +18,7 @@ chat:
gsm8k_accuracy: 28.12 gsm8k_accuracy: 28.12
race-high_accuracy: 53.12 race-high_accuracy: 53.12
deepseek-7b-chat-vllm: deepseek-7b-chat-vllm:
gsm8k_accuracy: 43.75 gsm8k_accuracy: 56.25
race-high_accuracy: 78.12 race-high_accuracy: 78.12
gemma2-2b-it-hf: gemma2-2b-it-hf:
gsm8k_accuracy: 50 gsm8k_accuracy: 50
@ -33,13 +33,13 @@ chat:
gsm8k_accuracy: 40.62 gsm8k_accuracy: 40.62
race-high_accuracy: 68.75 race-high_accuracy: 68.75
gemma-2-9b-it-turbomind: gemma-2-9b-it-turbomind:
gsm8k_accuracy: 71.88 gsm8k_accuracy: 68.75
race-high_accuracy: 84.38 race-high_accuracy: 84.38
gemma-2-27b-it-turbomind: gemma-2-27b-it-turbomind:
gsm8k_accuracy: 78.12 gsm8k_accuracy: 78.12
race-high_accuracy: 93.75 race-high_accuracy: 93.75
gemma-7b-it-vllm: gemma-7b-it-vllm:
gsm8k_accuracy: 31.25 gsm8k_accuracy: 28.12
race-high_accuracy: 68.75 race-high_accuracy: 68.75
internlm2_5-7b-chat-hf: internlm2_5-7b-chat-hf:
gsm8k_accuracy: 84.38 gsm8k_accuracy: 84.38
@ -48,25 +48,25 @@ chat:
gsm8k_accuracy: 65.62 gsm8k_accuracy: 65.62
race-high_accuracy: 87.5 race-high_accuracy: 87.5
internlm2_5-7b-chat-turbomind: internlm2_5-7b-chat-turbomind:
gsm8k_accuracy: 84.38 gsm8k_accuracy: 81.25
race-high_accuracy: 90.62 race-high_accuracy: 90.62
internlm2-chat-1.8b-turbomind: internlm2-chat-1.8b-turbomind:
gsm8k_accuracy: 28.12 gsm8k_accuracy: 25.00
race-high_accuracy: 84.38 race-high_accuracy: 84.38
internlm2-chat-1.8b-sft-turbomind: internlm2-chat-1.8b-sft-turbomind:
gsm8k_accuracy: 31.25 gsm8k_accuracy: 34.38
race-high_accuracy: 84.38 race-high_accuracy: 84.38
internlm2-chat-7b-lmdeploy: internlm2-chat-7b-lmdeploy:
gsm8k_accuracy: 59.38 gsm8k_accuracy: 59.38
race-high_accuracy: 84.38 race-high_accuracy: 87.50
internlm2-chat-7b-sft-turbomind: internlm2-chat-7b-sft-turbomind:
gsm8k_accuracy: 56.25 gsm8k_accuracy: 56.25
race-high_accuracy: 90.62 race-high_accuracy: 87.50
internlm3-8b-instruct-turbomind: internlm3-8b-instruct-turbomind:
gsm8k_accuracy: 68.75 gsm8k_accuracy: 65.62
race-high_accuracy: 87.5 race-high_accuracy: 87.5
internlm2-chat-7b-vllm: internlm2-chat-7b-vllm:
gsm8k_accuracy: 59.38 gsm8k_accuracy: 53.12
race-high_accuracy: 87.50 race-high_accuracy: 87.50
llama-3_1-8b-instruct-hf: llama-3_1-8b-instruct-hf:
gsm8k_accuracy: 84.38 gsm8k_accuracy: 84.38
@ -81,13 +81,13 @@ chat:
gsm8k_accuracy: 18.75 gsm8k_accuracy: 18.75
race-high_accuracy: 46.88 race-high_accuracy: 46.88
llama-3_1-8b-instruct-turbomind: llama-3_1-8b-instruct-turbomind:
gsm8k_accuracy: 81.25 gsm8k_accuracy: 84.38
race-high_accuracy: 90.62 race-high_accuracy: 90.62
llama-3_2-3b-instruct-turbomind: llama-3_2-3b-instruct-turbomind:
gsm8k_accuracy: 68.75 gsm8k_accuracy: 65.62
race-high_accuracy: 81.25 race-high_accuracy: 81.25
llama-3-8b-instruct-turbomind: llama-3-8b-instruct-turbomind:
gsm8k_accuracy: 68.75 gsm8k_accuracy: 65.62
race-high_accuracy: 84.38 race-high_accuracy: 84.38
mistral-7b-instruct-v0.2-hf: mistral-7b-instruct-v0.2-hf:
gsm8k_accuracy: 40.62 gsm8k_accuracy: 40.62
@ -100,12 +100,12 @@ chat:
race-high_accuracy: 81.25 race-high_accuracy: 81.25
mistral-nemo-instruct-2407-turbomind: mistral-nemo-instruct-2407-turbomind:
gsm8k_accuracy: 71.88 gsm8k_accuracy: 71.88
race-high_accuracy: 78.12 race-high_accuracy: 75
mistral-7b-instruct-v0.1-vllm: mistral-7b-instruct-v0.1-vllm:
gsm8k_accuracy: 34.38 gsm8k_accuracy: 34.38
race-high_accuracy: 65.62 race-high_accuracy: 65.62
mistral-7b-instruct-v0.2-vllm: mistral-7b-instruct-v0.2-vllm:
gsm8k_accuracy: 21.88 gsm8k_accuracy: 28.12
race-high_accuracy: 78.12 race-high_accuracy: 78.12
qwen2.5-0.5b-instruct-hf: qwen2.5-0.5b-instruct-hf:
gsm8k_accuracy: 34.38 gsm8k_accuracy: 34.38
@ -114,7 +114,7 @@ chat:
gsm8k_accuracy: 53.12 gsm8k_accuracy: 53.12
race-high_accuracy: 90.62 race-high_accuracy: 90.62
qwen2.5-0.5b-instruct-turbomind: qwen2.5-0.5b-instruct-turbomind:
gsm8k_accuracy: 31.25 gsm8k_accuracy: 28.12
race-high_accuracy: 43.75 race-high_accuracy: 43.75
qwen2.5-3b-instruct-turbomind: qwen2.5-3b-instruct-turbomind:
gsm8k_accuracy: 56.25 gsm8k_accuracy: 56.25
@ -132,10 +132,10 @@ chat:
gsm8k_accuracy: 56.25 gsm8k_accuracy: 56.25
race-high_accuracy: 84.38 race-high_accuracy: 84.38
qwen2-7b-instruct-turbomind: qwen2-7b-instruct-turbomind:
gsm8k_accuracy: 81.25 gsm8k_accuracy: 75.00
race-high_accuracy: 87.50 race-high_accuracy: 87.50
qwen1.5-0.5b-chat-vllm: qwen1.5-0.5b-chat-vllm:
gsm8k_accuracy: 3.12 gsm8k_accuracy: 6.25
race-high_accuracy: 53.12 race-high_accuracy: 53.12
yi-1.5-6b-chat-hf: yi-1.5-6b-chat-hf:
gsm8k_accuracy: 65.62 gsm8k_accuracy: 65.62
@ -144,13 +144,13 @@ chat:
gsm8k_accuracy: 75 gsm8k_accuracy: 75
race-high_accuracy: 93.75 race-high_accuracy: 93.75
yi-1.5-6b-chat-turbomind: yi-1.5-6b-chat-turbomind:
gsm8k_accuracy: 62.5 gsm8k_accuracy: 59.38
race-high_accuracy: 84.38 race-high_accuracy: 84.38
yi-1.5-9b-chat-turbomind: yi-1.5-9b-chat-turbomind:
gsm8k_accuracy: 71.88 gsm8k_accuracy: 78.12
race-high_accuracy: 93.75 race-high_accuracy: 93.75
deepseek-v2_lite-chat-turbomind: deepseek-v2_lite-chat-turbomind:
gsm8k_accuracy: 37.5 gsm8k_accuracy: 43.75
race-high_accuracy: 71.88 race-high_accuracy: 71.88
gemma2-27b-it-hf: gemma2-27b-it-hf:
gsm8k_accuracy: 71.88 gsm8k_accuracy: 71.88
@ -165,7 +165,7 @@ chat:
gsm8k_accuracy: 81.25 gsm8k_accuracy: 81.25
race-high_accuracy: 87.50 race-high_accuracy: 87.50
mistral-small-instruct-2409-turbomind: mistral-small-instruct-2409-turbomind:
gsm8k_accuracy: 81.25 gsm8k_accuracy: 78.12
race-high_accuracy: 87.50 race-high_accuracy: 87.50
phi-4: phi-4:
gsm8k_accuracy: 81.25 gsm8k_accuracy: 81.25
@ -174,16 +174,16 @@ chat:
gsm8k_accuracy: 71.88 gsm8k_accuracy: 71.88
race-high_accuracy: 96.88 race-high_accuracy: 96.88
qwen2.5-14b-instruct-turbomind: qwen2.5-14b-instruct-turbomind:
gsm8k_accuracy: 68.75 gsm8k_accuracy: 71.88
race-high_accuracy: 93.75 race-high_accuracy: 96.88
yi-1.5-34b-chat-turbomind: yi-1.5-34b-chat-turbomind:
gsm8k_accuracy: 75.00 gsm8k_accuracy: 71.88
race-high_accuracy: 93.75 race-high_accuracy: 93.75
deepseek-67b-chat-turbomind: deepseek-67b-chat-turbomind:
gsm8k_accuracy: 75.00 gsm8k_accuracy: 71.88
race-high_accuracy: 78.12 race-high_accuracy: 75.00
deepseek-r1-distill-qwen-32b-turbomind: deepseek-r1-distill-qwen-32b-turbomind:
gsm8k_accuracy: 25 gsm8k_accuracy: 31.25
race-high_accuracy: 90.62 race-high_accuracy: 90.62
llama-3_3-70b-instruct-turbomind: llama-3_3-70b-instruct-turbomind:
gsm8k_accuracy: 93.75 gsm8k_accuracy: 93.75
@ -192,19 +192,19 @@ chat:
gsm8k_accuracy: 87.50 gsm8k_accuracy: 87.50
race-high_accuracy: 93.75 race-high_accuracy: 93.75
nvidia-3_1-Nemotron-70b-instruct-HF-turbomind: nvidia-3_1-Nemotron-70b-instruct-HF-turbomind:
gsm8k_accuracy: 93.75 gsm8k_accuracy: 90.62
race-high_accuracy: 50.00 race-high_accuracy: 53.12
qwen2.5-72b-instruct-turbomind: qwen2.5-72b-instruct-turbomind:
gsm8k_accuracy: 81.25 gsm8k_accuracy: 78.12
race-high_accuracy: 90.62 race-high_accuracy: 90.62
deepseek-r1-distill-llama-70b-turbomind: deepseek-r1-distill-llama-70b-turbomind:
gsm8k_accuracy: 40.62 gsm8k_accuracy: 50.00
race-high_accuracy: 90.62 race-high_accuracy: 87.50
deepseek-v2_5-1210-turbomind: deepseek-v2_5-1210-turbomind:
gsm8k_accuracy: 90.62 gsm8k_accuracy: 90.62
race-high_accuracy: 84.38 race-high_accuracy: 84.38
mixtral-8x22b-instruct-v0.1-turbomind: mixtral-8x22b-instruct-v0.1-turbomind:
gsm8k_accuracy: 78.12 gsm8k_accuracy: 75.00
race-high_accuracy: 78.12 race-high_accuracy: 78.12
mixtral-8x22b-instruct-v0.1-vllm: mixtral-8x22b-instruct-v0.1-vllm:
gsm8k_accuracy: 78.12 gsm8k_accuracy: 78.12
@ -222,11 +222,11 @@ base:
winogrande_accuracy: 71.88 winogrande_accuracy: 71.88
deepseek-7b-base-turbomind: deepseek-7b-base-turbomind:
gsm8k_accuracy: 18.75 gsm8k_accuracy: 18.75
GPQA_diamond_accuracy: 0 GPQA_diamond_accuracy: 3.12
race-high_accuracy: 43.75 race-high_accuracy: 50.00
winogrande_accuracy: 84.38 winogrande_accuracy: 84.38
deepseek-moe-16b-base-vllm: deepseek-moe-16b-base-vllm:
gsm8k_accuracy: 21.88 gsm8k_accuracy: 25.00
GPQA_diamond_accuracy: 0 GPQA_diamond_accuracy: 0
race-high_accuracy: 25 race-high_accuracy: 25
winogrande_accuracy: 68.75 winogrande_accuracy: 68.75
@ -253,15 +253,15 @@ base:
gemma-2-9b-turbomind: gemma-2-9b-turbomind:
gsm8k_accuracy: 68.75 gsm8k_accuracy: 68.75
GPQA_diamond_accuracy: 0 GPQA_diamond_accuracy: 0
race-high_accuracy: 18.75 race-high_accuracy: 84.38
winogrande_accuracy: 46.88 winogrande_accuracy: 81.25
gemma-2b-vllm: gemma-2b-vllm:
gsm8k_accuracy: 15.62 gsm8k_accuracy: 15.62
GPQA_diamond_accuracy: 3.12 GPQA_diamond_accuracy: 3.12
race-high_accuracy: 28.12 race-high_accuracy: 28.12
winogrande_accuracy: 68.75 winogrande_accuracy: 68.75
gemma-7b-vllm: gemma-7b-vllm:
gsm8k_accuracy: 43.75 gsm8k_accuracy: 59.38
GPQA_diamond_accuracy: 6.25 GPQA_diamond_accuracy: 6.25
race-high_accuracy: 81.25 race-high_accuracy: 81.25
winogrande_accuracy: 81.25 winogrande_accuracy: 81.25
@ -276,8 +276,8 @@ base:
race-high_accuracy: 62.5 race-high_accuracy: 62.5
winogrande_accuracy: 78.12 winogrande_accuracy: 78.12
internlm2-1.8b-turbomind: internlm2-1.8b-turbomind:
gsm8k_accuracy: 6.25 gsm8k_accuracy: 12.50
GPQA_diamond_accuracy: 12.5 GPQA_diamond_accuracy: 9.38
race-high_accuracy: 71.88 race-high_accuracy: 71.88
winogrande_accuracy: 75 winogrande_accuracy: 75
internlm2_5-7b-turbomind: internlm2_5-7b-turbomind:
@ -286,13 +286,13 @@ base:
race-high_accuracy: 93.75 race-high_accuracy: 93.75
winogrande_accuracy: 87.5 winogrande_accuracy: 87.5
internlm2-7b-turbomind: internlm2-7b-turbomind:
gsm8k_accuracy: 59.38 gsm8k_accuracy: 53.12
GPQA_diamond_accuracy: 34.38 GPQA_diamond_accuracy: 25.00
race-high_accuracy: 78.12 race-high_accuracy: 78.12
winogrande_accuracy: 71.88 winogrande_accuracy: 71.88
internlm2-base-7b-turbomind: internlm2-base-7b-turbomind:
gsm8k_accuracy: 28.12 gsm8k_accuracy: 25.00
GPQA_diamond_accuracy: 31.25 GPQA_diamond_accuracy: 34.38
race-high_accuracy: 71.88 race-high_accuracy: 71.88
winogrande_accuracy: 62.50 winogrande_accuracy: 62.50
llama-2-7b-hf: llama-2-7b-hf:
@ -311,8 +311,8 @@ base:
race-high_accuracy: 65.62 race-high_accuracy: 65.62
winogrande_accuracy: 65.62 winogrande_accuracy: 65.62
llama-3.1-8b-turbomind: llama-3.1-8b-turbomind:
gsm8k_accuracy: 59.38 gsm8k_accuracy: 56.25
GPQA_diamond_accuracy: 15.62 GPQA_diamond_accuracy: 9.38
race-high_accuracy: 78.12 race-high_accuracy: 78.12
winogrande_accuracy: 78.12 winogrande_accuracy: 78.12
llama-3-8b-turbomind: llama-3-8b-turbomind:
@ -332,12 +332,12 @@ base:
winogrande_accuracy: 71.88 winogrande_accuracy: 71.88
qwen2.5-1.5b-turbomind: qwen2.5-1.5b-turbomind:
gsm8k_accuracy: 59.38 gsm8k_accuracy: 59.38
GPQA_diamond_accuracy: 18.75 GPQA_diamond_accuracy: 21.88
race-high_accuracy: 75 race-high_accuracy: 78.12
winogrande_accuracy: 71.88 winogrande_accuracy: 71.88
qwen2.5-7b-turbomind: qwen2.5-7b-turbomind:
gsm8k_accuracy: 71.88 gsm8k_accuracy: 78.12
GPQA_diamond_accuracy: 18.75 GPQA_diamond_accuracy: 21.88
race-high_accuracy: 87.5 race-high_accuracy: 87.5
winogrande_accuracy: 75.00 winogrande_accuracy: 75.00
qwen1.5-moe-a2.7b-hf: qwen1.5-moe-a2.7b-hf:
@ -361,18 +361,18 @@ base:
race-high_accuracy: 87.5 race-high_accuracy: 87.5
winogrande_accuracy: 68.75 winogrande_accuracy: 68.75
qwen2-1.5b-turbomind: qwen2-1.5b-turbomind:
gsm8k_accuracy: 59.38 gsm8k_accuracy: 56.25
GPQA_diamond_accuracy: 6.25 GPQA_diamond_accuracy: 12.50
race-high_accuracy: 81.25 race-high_accuracy: 81.25
winogrande_accuracy: 75 winogrande_accuracy: 75
qwen2-7b-turbomind: qwen2-7b-turbomind:
gsm8k_accuracy: 62.5 gsm8k_accuracy: 65.62
GPQA_diamond_accuracy: 12.5 GPQA_diamond_accuracy: 12.5
race-high_accuracy: 87.5 race-high_accuracy: 87.5
winogrande_accuracy: 75 winogrande_accuracy: 75
qwen1.5-0.5b-vllm: qwen1.5-0.5b-vllm:
gsm8k_accuracy: 9.38 gsm8k_accuracy: 9.38
GPQA_diamond_accuracy: 0 GPQA_diamond_accuracy: 3.12
race-high_accuracy: 56.25 race-high_accuracy: 56.25
winogrande_accuracy: 59.38 winogrande_accuracy: 59.38
yi-1.5-6b-hf: yi-1.5-6b-hf:
@ -386,7 +386,7 @@ base:
race-high_accuracy: 87.5 race-high_accuracy: 87.5
winogrande_accuracy: 59.38 winogrande_accuracy: 59.38
yi-1.5-9b-turbomind: yi-1.5-9b-turbomind:
gsm8k_accuracy: 78.12 gsm8k_accuracy: 75.00
GPQA_diamond_accuracy: 40.62 GPQA_diamond_accuracy: 40.62
race-high_accuracy: 87.5 race-high_accuracy: 87.5
winogrande_accuracy: 65.62 winogrande_accuracy: 65.62
@ -406,13 +406,13 @@ base:
race-high_accuracy: 93.75 race-high_accuracy: 93.75
winogrande_accuracy: 78.12 winogrande_accuracy: 78.12
qwen2.5-32b-turbomind: qwen2.5-32b-turbomind:
gsm8k_accuracy: 84.38 gsm8k_accuracy: 90.62
GPQA_diamond_accuracy: 28.12 GPQA_diamond_accuracy: 31.25
race-high_accuracy: 93.75 race-high_accuracy: 93.75
winogrande_accuracy: 81.25 winogrande_accuracy: 81.25
deepseek-67b-base-turbomind: deepseek-67b-base-turbomind:
gsm8k_accuracy: 59.38 gsm8k_accuracy: 62.50
GPQA_diamond_accuracy: 34.38 GPQA_diamond_accuracy: 31.25
race-high_accuracy: 78.12 race-high_accuracy: 78.12
winogrande_accuracy: 81.25 winogrande_accuracy: 81.25
llama-3-70b-turbomind: llama-3-70b-turbomind:
@ -422,11 +422,11 @@ base:
winogrande_accuracy: 84.38 winogrande_accuracy: 84.38
qwen2.5-72b-turbomind: qwen2.5-72b-turbomind:
gsm8k_accuracy: 84.38 gsm8k_accuracy: 84.38
GPQA_diamond_accuracy: 31.25 GPQA_diamond_accuracy: 40.62
race-high_accuracy: 93.75 race-high_accuracy: 93.75
winogrande_accuracy: 87.5 winogrande_accuracy: 87.5
deepseek-v2-turbomind: deepseek-v2-turbomind:
gsm8k_accuracy: 65.62 gsm8k_accuracy: 65.62
GPQA_diamond_accuracy: 9.38 GPQA_diamond_accuracy: 3.12
race-high_accuracy: 93.75 race-high_accuracy: 93.75
winogrande_accuracy: 81.25 winogrande_accuracy: 81.25