| 1 |
GPT-5 (high)
| 0.76 |
OpenAI
|
| 2 |
GPT-5 (medium)
| 0.73 |
OpenAI
|
| 3 |
o3
| 0.69 |
OpenAI
|
| 4 |
O3 Pro
| 0.69 |
OpenAI
|
| 5 |
O3 Mini
| 0.69 |
OpenAI
|
| 6 |
O3 Mini High
| 0.69 |
OpenAI
|
| 7 |
Grok 4
| 0.68 |
xAI
|
| 8 |
Qwen3 235B 2507 (Reasoning)
| 0.67 |
Alibaba
|
| 9 |
Gemini 2.5 Pro
| 0.66 |
Google
|
| 10 |
Gemini 2 5 Pro 05 06
| 0.66 |
Google
|
| 11 |
Gemini 2 5 Pro 03 25
| 0.66 |
Google
|
| 12 |
Gpt 5 Mini
| 0.66 |
OpenAI
|
| 13 |
Claude 4 Sonnet Thinking
| 0.65 |
Anthropic
|
| 14 |
Gemini 2.5 Flash (Reasoning)
| 0.62 |
Google
|
| 15 |
Gemini 2 5 Flash Reasoning 04 2025
| 0.62 |
Google
|
| 16 |
GPT-4.1
| 0.61 |
OpenAI
|
| 17 |
GPT-5 (low)
| 0.59 |
OpenAI
|
| 18 |
o4-mini (high)
| 0.55 |
OpenAI
|
| 19 |
DeepSeek R1 0528
| 0.55 |
Unknown
|
| 20 |
MiniMax M1 80k
| 0.54 |
Unknown
|
| 21 |
GPT-4o (ChatGPT)
| 0.53 |
OpenAI
|
| 22 |
MiniMax M1 40k
| 0.52 |
Unknown
|
| 23 |
Gemini 2.5 Flash-Lite (Reasoning)
| 0.51 |
Google
|
| 24 |
Kimi K2
| 0.51 |
Unknown
|
| 25 |
gpt-oss-120B (high)
| 0.51 |
OpenAI
|
| 26 |
Grok 3 mini Reasoning (high)
| 0.50 |
xAI
|
| 27 |
GLM-4.5
| 0.48 |
Zhipu AI
|
| 28 |
Glm 4 5 Air
| 0.48 |
Zhipu AI
|
| 29 |
Llama 4 Maverick
| 0.46 |
Meta
|
| 30 |
Gemini 2 5 Flash
| 0.46 |
Google
|
| 31 |
Claude 4 Sonnet
| 0.44 |
Anthropic
|
| 32 |
Qwen3 Coder 480B
| 0.42 |
Alibaba
|
| 33 |
Qwen3 Coder 480b A35b Instruct
| 0.42 |
Alibaba
|
| 34 |
Gpt 4 1 Mini
| 0.42 |
OpenAI
|
| 35 |
DeepSeek V3 0324 (Mar '25)
| 0.41 |
Unknown
|
| 36 |
Gpt 5 Nano
| 0.40 |
OpenAI
|
| 37 |
Claude 4 Opus
| 0.36 |
Anthropic
|
| 38 |
Llama Nemotron Super 49B v1.5 (Reasoning)
| 0.34 |
Meta
|
| 39 |
Claude 4 Opus Thinking
| 0.34 |
Anthropic
|
| 40 |
Gemini 2.5 Flash-Lite
| 0.31 |
Google
|
| 41 |
Nova Premier
| 0.30 |
Unknown
|
| 42 |
Devstral Medium
| 0.29 |
Unknown
|
| 43 |
Gemini 2.0 Flash
| 0.28 |
Google
|
| 44 |
Mistral Medium 3
| 0.28 |
Unknown
|
| 45 |
Llama 4 Scout
| 0.26 |
Meta
|
| 46 |
GPT-5 (minimal)
| 0.25 |
OpenAI
|
| 47 |
Llama Nemotron Super 49b V1 5
| 0.22 |
Meta
|
| 48 |
Mistral Medium 3 1
| 0.20 |
Unknown
|
| 49 |
Nova Pro
| 0.19 |
Unknown
|
| 50 |
gpt-oss-20B (high)
| 0.19 |
OpenAI
|
| 51 |
Nvidia Nemotron Nano 9b V2 Reasoning
| 0.18 |
Unknown
|
| 52 |
Command A
| 0.18 |
Unknown
|
| 53 |
Nova Lite
| 0.18 |
Unknown
|
| 54 |
Mistral Small 3 2
| 0.17 |
Unknown
|
| 55 |
Gpt 4 1 Nano
| 0.17 |
OpenAI
|
| 56 |
Llama 3.1 8B
| 0.16 |
Meta
|
| 57 |
Llama 3.3 70B
| 0.15 |
Meta
|
| 58 |
EXAONE 4.0 32B (Reasoning)
| 0.14 |
Unknown
|
| 59 |
Mistral Small 3 1
| 0.14 |
Unknown
|
| 60 |
Nova Micro
| 0.10 |
Unknown
|
| 61 |
EXAONE 4.0 32B
| 0.08 |
Unknown
|
| 62 |
Llama Nemotron Ultra Reasoning
| 0.07 |
Meta
|
| 63 |
Gemma 3 12b
| 0.07 |
Unknown
|
| 64 |
Granite 3.3 8B
| 0.04 |
Unknown
|
| 65 |
Granite 3 3 8b Instruct
| 0.04 |
Unknown
|