Math Benchmark Sheet Shows 90.43% Top Accuracy at Just $1.21 per Run
teortaxesTex · x · 2026-11-12
teortaxesTex shared a screenshot of math/proof benchmarks (ArXivMath, LeanLean, etc.): GPT-6.1 Sol (max) leads with 90.43% accuracy at $1.21 cost; Gemini 4 Argon (high) hits 82.98% but costs $3.26 with 206k tokens; Claude-Opus-5.5 (high) scores 79.79% at $2.19. Kimi K3.1 Pro, DeepSeek-V4.1-Flash-1017 and Mistral Large 4 trail. The poster credits the strong low-cost showing to superior data engineering. Treat with caution as the results are unverified.
Related event: Math benchmarks: GPT-6.1 Sol leads as open models shine(2 posts)→
More from Models
- ICLR abstract word-frequency shift: 'novel' and 'comprehensive' plummet as LLM fingerprints fade — y_m_asano · 2026-11-12
- Codex quota reset caveat: using a reset pushes your next refresh 7 days out — JeremyNguyenPhD · 2026-11-12
- Gemini 4 Carbon hands-on: beats DeepSeek Flash, priced at Sonnet level not Opus — oran_ge · 2026-11-12
- Doubao Work adds third-party models; DeepSeek V4.1 Flash edits an 8-min video for $0.02 — op7418 · 2026-11-12
- LLMs play Among Us against each other; Haiku 5.5 kills then instantly self-reports — Rasmic · 2026-11-12
- Kimi K3.1-Pro abliterated variant hits Hugging Face, claiming 95% refusal removal — zebird0 · 2026-11-12