THE FORGE RANKINGS·2026-08-30

GPT-5.1 (2025-11-13)

OpenAI
26
RANK of 37 ranked
FERROX INDEX47.4 weighted mean of category positions
GRADED back of the field
EVIDENCE9 / 32 benchmarks measured
QUALITYFULL every category rests on independent benchmarks

No measurement in Preference. That weight was redistributed, which is the same as assuming this model would have scored its own average there. It is an assumption, not a measurement.

Compared to what

Each rail is one classification. Every ranked model measured on it is a tick; this model is the orange marker. A hatched rail means this model has no measurement in that classification and its weight was redistributed.

Agents

29of 37 measured
32.5
13.1median 38.963.0

Coding

19of 37 measured
50.0
22.4median 50.070.7

Reasoning

33of 37 measured
33.6
18.1median 62.893.0

Preference

no qualifying measurement
53.1median 71.882.5

Every measurement, and the field behind it

One card per benchmark this model has been measured on. The rail shows where it sits against every other ranked model measured on the same benchmark. Where the evaluator keys on a harness, the harness is named, because the same model scores differently under a different one.

ALE-Bench

18/35
1192 best 2177 · GPT-5.6 Sol
ALE-Bench (Sakana AI with AtCoder) CC-BY-4.0 high

Not measured

23/32
  • LMArena Agent
  • LMArena Text (style-controlled)
  • DeepSWE
  • FrontierCode
  • LMArena WebDev
  • METR time horizons
  • Terminal-Bench 4.0
  • Aider Polyglot
  • OSWorld
  • Cybench
  • BrowseComp
  • IMOAnswerBench
  • SWE-bench Multilingual
  • AIME
  • CyberGym
  • HMMT
  • MCP-Atlas
  • SWE-bench Pro
  • Tau2-Bench Airline
  • Tau2-Bench Banking
  • Tau2-Bench Retail
  • Tau2-Bench Telecom
  • Tool-Decathlon
A missing benchmark is not a zero and is never scored as one.

Check it yourself

Every number on this page, with who measured it, the interval they published, the harness it was run under, and where to go and read it. Nothing here was measured by Ferrox Labs.

BenchmarkClassPublishedInterval (normalised) Measured byLicenceHarness / effort
APEX Agents agents 17.5% 12.4 to 22.6 APEX CC-BY-4.0 source
Terminal-Bench 2 agents 47.6% 42.1 to 53.1 Terminal-Bench v2 Leaderboard CC-BY-4.0 Terminus 2 / medium source
ALE-Bench coding 1192 not published ALE-Bench (Sakana AI with AtCoder) CC-BY-4.0 / high source
SWE-bench Verified (Epoch's own run) coding 65.9% 61.7 to 70.1 Epoch AI CC-BY-4.0 / high source
ARC-AGI-2 reasoning 1.9% not published ARC Prize CC-BY-4.0 / low source
FrontierMath reasoning 17.3% 12.9 to 21.7 Epoch AI CC-BY-4.0 / low source
GPQA Diamond (Epoch's own run) reasoning 85.0% 80.9 to 89.2 Epoch AI CC-BY-4.0 / medium source
Humanity's Last Exam reasoning 6.8% 4.9 to 8.7 Humanity’s Last Exam (CAIS / Scale AI) CC-BY-4.0 / none source
OTIS Mock AIME 2024-2025 reasoning 63.9% 52.4 to 75.4 Epoch AI CC-BY-4.0 / low source

Configurations rolled up: 6. Rule: median observed configuration per benchmark (lower median, always a real measurement). Harnesses seen: terminus-2.

Snapshot 2026-08-30-62e4e85f043b, manifest dc46131315046f1e. Grades are positional: position in the measured field, as a percentile of rank among ranked entries, n=37.