GPT-6.1 sol reportedly tops pure reasoning on HLE-Diamond at 67.4% using just 4k tokens
haider1 · x · 2026-09-30
X user haider1 shared (unofficial) HLE-Diamond results for GPT-6.1 sol:
- Overall: 6.1 sol at 53.2%, vs Fable 5.1 at 50.7% and Opus 5.5 at 54.6%
- On pure reasoning, 6.1 sol leads both: 67.4% vs 60.8% for Fable 5.1 and 62.4% for Opus 5.5
- Token efficiency is the standout: 4k tokens, compared to 16k for Fable and 10k for Opus
If accurate, the model matches or beats competitors while consuming a quarter to half their tokens. Third-party numbers, not yet officially confirmed.
Related event: GPT-6.1 Sol Launches with Astra-Level Intelligence at a Fifth of the Price(32 posts)→
More from Models
- Stealth Model 'silicon-2' Surfaces in Devin, Suspected to Be Anthropic's Next Model — kimmonismus · 2026-11-16
- Google hides Gemini model label in AI Mode, rolls Gemini 4 Carbon to Pro subscribers — gaganghotra_ · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- Nathan Lambert calls out Ethan Mollick for 'selectively ignoring' Kimi in model comparisons — natolambert · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- Unsloth Q8 crushes default Q3 in a self-hosted test over 331 financial PDFs — No_Cartographer3953 · 2026-11-16