Atlas

Benchmarks

← All benchmarks

LisanBench Path Length

Games · 2025-05-30

LisanBench Path Length sums each model's valid edit-distance-one word-chain transitions across 50 starting words after averaging the three trials for each word. Chains must begin with the required word, use dictionary words, and never repeat a word.

Top models (higher is better)

ModelScore
Muse Wonder Full32190
Muse Wonder27973
Claude Opus 5.524029
DeepSeek V4.1 Flash 101721107
Claude Opus 515428
Claude Fable 5.115100
Opus 4.714400
Opus 4.614206
Claude Sonnet 5.513787
Claude Fable 513680
Claude Haiku 5.512897
Sonnet 4.612060
Kimi K310521
GPT-5.59845
Opus 4.89463
GPT-6.1 Sol8736
GPT-6 Sol8222
Gemini 4 Argon7560
GPT-6 Astra7393
Gemini 3.1 Pro Preview6445
Sonnet 55724
Opus 4.55513
GPT-5.45335
DeepSeek-V3.2-Speciale5073
GPT-5.6 Sol4699
Gemini 3 Pro Preview4677
GPT-5.6 Luna4181
Gemini 3.5 Flash4123
Grok 44042
GPT-6 Luna3864
Grok 4.203856
GPT-5.23592
o33309
GPT-5.6 Terra3303
DeepSeek-V4-Pro3256
DeepSeek-V4-Flash2789
Grok 4 Fast2750
Sonnet 4.52665
Step 3.5 Flash2410
DeepSeek-V3.22348
Loading Atlas data…