Legal Eval: Full Pass Rate Correlates with Token Output
ArtificialAnlys · x · 2026-07-08
Artificial Analysis points out that a model's full pass rate is generally tied to its workload per task. Fable 5 generated 117,000 output tokens per task to achieve a 14.2% full pass rate; Opus 4.8 and GLM-5.2 generated 111,000 and 78,000 tokens respectively to reach 7.5%. Sonnet 5 generated the most output in this evaluation at 179,000 tokens per task, yet only achieved a 5.0% pass rate.
Related event: Artificial Analysis Releases Harvey Legal Agent Benchmark Results(8 posts)→
More from Models
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11