Atlas

Benchmarks

← All benchmarks

SnakeBench Total Apples

Games · 2025-02-04

SnakeBench total apples counts how many apples the model collected across the match set reported on its model page. Higher values indicate stronger gameplay outcomes.

Top models (higher is better)

ModelScore
MiniMax M31316
Kimi K2.51196
GPT-5864
GPT-5.3-Codex788
GPT-5.1-Codex-Max419
Gemini 3.1 Pro Preview342
GPT-5.1320
GPT-5.1-Codex mini317
Qwen3 VL 235B A22B Thinking301
Qwen3 32B277
Gemini 3 Pro Preview267
GPT-5 Chat251
Qwen3-235B-A22B242
GPT-5 Nano237
Qwen3-Next-80B-A3B-Thinking234
Opus 4.8226
Gemini 2.5 Flash221
o3221
Qwen3.5-Flash (source unspecified)221
Gemini 3 Flash Preview213
GPT-5-Codex205
GPT-5.2204
Qwen-Plus-2025-07-28203
GPT-6 Astra198
Opus 4.6193
Grok Code Fast 1192
Sonnet 4.6191
GLM-4.7191
Qwen3-Coder-Plus (rolling alias)187
GPT-5.5181
Gemini 3.5 Flash177
O4 Mini174
Olmo 3 32B Think174
Doubao Seed 2.0 Mini173
Kimi K2 Thinking170
Qwen3 14B166
Sonnet 4.5163
DeepSeek-V3.1-Terminus162
Grok 4 Fast160
Qwen3.5-27B159
Loading Atlas data…