RankingFrontierMath Tier 1-3 (v2) · v2

FrontierMath Tier 1-3 (v2) · v2

Data updated 12 Sept 2026

Bucket
Hard reasoning
Unit
percent
Direction
Higher is better
Version
v2
Display harness
GPT-5.6: Frontier intelligence that scales with your ambition
Board
https://openai.com/index/gpt-5-6/

Compare published benchmark results with category weights →

Models

ModelScoreHarnessEvidenceSource-recorded date
GPT-5.6 SolOpenAI89%
Reported settings & source

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Academic table / FrontierMath Tier 1-3 (v2) / GPT‑5.6 Sol · reviewed 2026-09-06

GPT-5.6: Frontier intelligence that scales with your ambitionlab self-report2026-09-06
Claude Fable 5Anthropic87%
Reported settings & source

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Academic table / FrontierMath Tier 1-3 (v2) / Claude Fable 5 · reviewed 2026-09-06

GPT-5.6: Frontier intelligence that scales with your ambitionlab self-report2026-09-06
GPT-5.5OpenAI85.3%
Reported settings & source

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Academic table / FrontierMath Tier 1-3 (v2) / GPT‑5.5 · reviewed 2026-09-06

GPT-5.6: Frontier intelligence that scales with your ambitionlab self-report2026-09-06
GPT-5.6 TerraOpenAI84.9%
Reported settings & source

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Academic table / FrontierMath Tier 1-3 (v2) / GPT‑5.6 Terra · reviewed 2026-09-06

GPT-5.6: Frontier intelligence that scales with your ambitionlab self-report2026-09-06
Claude Opus 4.8Anthropic80%
Reported settings & source

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Academic table / FrontierMath Tier 1-3 (v2) / Claude Opus 4.8 · reviewed 2026-09-06

GPT-5.6: Frontier intelligence that scales with your ambitionlab self-report2026-09-06
GPT-5.6 LunaOpenAI78.6%
Reported settings & source

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Academic table / FrontierMath Tier 1-3 (v2) / GPT‑5.6 Luna · reviewed 2026-09-06

GPT-5.6: Frontier intelligence that scales with your ambitionlab self-report2026-09-06
Gemini 3.1 ProGoogle59.6%
Reported settings & source

Launch table reported configuration; per-cell reasoning effort unspecified

Provider-published result; comparator measurements are not automatically independently reproduced.

GPT-5.6: Frontier intelligence that scales with your ambition · Academic table / FrontierMath Tier 1-3 (v2) / Gemini 3.1 Pro Preview · reviewed 2026-09-06

GPT-5.6: Frontier intelligence that scales with your ambitionlab self-report2026-09-06