RLTasksby ulam.ai
Models / OpenAI

OpenAI / MODEL EVIDENCE

GPT-5.1 Codex

7 benchmarks · 14 observations · 9 sources

Scores at a glance

7 benchmarks · large dot: GPT-5.1 Codex; small dots: closest models where reported

MMLU-Pro ↗86.01%
84.8689.76

GPT-5.1 Codex (High) · MMLU-Pro · AA implementation ↗

Terminal-Bench 2.0 ↗57.75%
3.0784.72

GPT-5.1 Codex · Terminal Bench · Accuracy mean · % ↗

4 more reported results

53.48% · GPT-5.1 Codex · Terminal Bench · Accuracy mean · % · Epoch AI · Terminal Bench ↗

36.85% · GPT-5.1 Codex · Terminal Bench · Accuracy mean · % · Epoch AI · Terminal Bench ↗

57.8% · GPT-5.1 Codex · Terminal Bench · Accuracy mean · % · Epoch AI · Terminal Bench ↗

36.9% · GPT-5.1 Codex · Terminal Bench · Accuracy mean · % · Epoch AI · Terminal Bench ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

18.6 percentile-point gap

3 of 3 shared benchmark comparisons

19.9 percentile-point gap

3 of 3 shared benchmark comparisons

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. Arena leaderboard — WebDev evaluation ↗

    Arena

  2. AIME 2025 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  3. Global-MMLU-Lite Benchmark | Artificial Analysis ↗

    Artificial Analysis

  4. LiveCodeBench Benchmark | Artificial Analysis ↗

    Artificial Analysis

  5. MMLU-Pro Benchmark | Artificial Analysis ↗

    Artificial Analysis

  6. Terminal-Bench 2.0 ↗

    Epoch AI

  7. Terminal-Bench 2.0 leaderboard ↗

    Terminal-Bench Team

  8. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  9. Vibe Code Bench — evaluation methodology and results ↗

    Vals AI · 2026

Release dates reported by sources

2025-11-12 · 2025-11-13

Names used in source tables

GPT 5.1 Codex · GPT 5.1 Codex (OpenHands) · GPT 5.1 Codex Max · GPT 5.1 Codex Max (OpenHands) · GPT-5.1 Codex · GPT-5.1 Codex (High)