Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Meta-Evaluation on Aggregated Benchmarks (AIME, ARC, GSM8K, HE, MMLU, IT, RU, BFCL)
Loading...
2.4
Overall Average Rank
GPT-5 nano
1.888
5.344
8.8
12.256
May 8, 2026
Overall Average Rank
Updated 23d ago
Evaluation Results
Method
Method
Links
Overall Average Rank
GPT-5 nano
2026.05
2.4
Qwen3-8B
Parameters=8B
2026.05
2.6
Qwen3-4B
Parameters=4B
2026.05
4.2
gpt-oss-20b
Parameters=20B
2026.05
4.5
Ministral-3-8B
Parameters=8B
2026.05
5
gemma-3-12b-it
Parameters=12B, Instru...
2026.05
5.1
EngGPT2-16B-A3B
Parameters=16B
2026.05
8
Llama-3.1-8B
Parameters=8B
2026.05
8.2
gemma-3-4b-it
Parameters=4B, Instruc...
2026.05
9.1
Moonlight-16B-A3B
Parameters=16B
2026.05
9.9
Llama-3.2-3B
Parameters=3B
2026.05
10.4
LLaMAntino-3-8B
Parameters=8B
2026.05
11
Velvet-14B
Parameters=14B
2026.05
12.4
FastwebMIIA-7B
Parameters=7B
2026.05
13.4
deepseek-moe-16b
Parameters=16B
2026.05
14.5
Minerva-7B
Parameters=7B
2026.05
15.2
Feedback
Search any
task
Search any
task