RLTasksby ulam.ai
Models / OpenAI

OpenAI / MODEL EVIDENCE

GPT-5 (minimal)

11 benchmarks · 18 observations · 11 sources · released 2025-08-07

Scores at a glance

11 benchmarks · large dot: GPT-5 (minimal); small dots: closest models where reported

GPQA Diamond ↗71.72%
9.2896.4

GPT-5 (minimal) · GPQA diamond · Best score (across scorers) · % ↗

BALROG ↗32.8%
3.768.3

GPT-5 (minimal) · Balrog · Average progress · % ↗

GAIA-2 ↗31.9%
7.169.2

GPT-5 (minimal) · GAIA-2 · Gaia2 full · Execution pass@1 · baseline ReAct · three runs ↗

7 more reported results

26.2% · GPT-5 (minimal) · GAIA-2 · Gaia2 full · Search pass@1 · baseline ReAct · three runs · Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments ↗

20.6% · GPT-5 (minimal) · GAIA-2 · Gaia2 full · Ambiguity pass@1 · baseline ReAct · three runs · Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments ↗

19.2% · GPT-5 (minimal) · GAIA-2 · Gaia2 full · Adaptability pass@1 · baseline ReAct · three runs · Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments ↗

5.2% · GPT-5 (minimal) · GAIA-2 · Gaia2 full · Time pass@1 · baseline ReAct · three runs · Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments ↗

13.1% · GPT-5 (minimal) · GAIA-2 · Gaia2 full · Noise pass@1 · baseline ReAct · three runs · Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments ↗

11.5% · GPT-5 (minimal) · GAIA-2 · Gaia2 full · Agent2Agent pass@1 · baseline ReAct · three runs · Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments ↗

18.2% · GPT-5 (minimal) · GAIA-2 · Gaia2 full · Overall pass@1 · baseline ReAct · three runs · Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments ↗

Closest models by score

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

o1 →OpenAI
6.6 percentile-point gap

4 of 5 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. Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments — published result table ↗

    Froger, Romain, Andrews, Pierre, Bettini, Matteo, Budhiraja, Amar, Cabral, Ricardo Silveira, Do, Virginie et al. · 2026

    All 24 authors

    Froger, Romain, Andrews, Pierre, Bettini, Matteo, Budhiraja, Amar, Cabral, Ricardo Silveira, Do, Virginie, Garreau, Emilien, Gaya, Jean-Baptiste, Laurençon, Hugo, Lecanu, Maxime, Malkan, Kunal, Mekala, Dheeraj, Ménard, Pierre, Bertran, Gerard Moreno-Torres, Piterbarg, Ulyana, Plekhanov, Mikhail, Rita, Mathieu, Rusakov, Andrey, Vorotilov, Vladislav, Wang, Mengjue, Yu, Ian, Benhalloum, Amine, Mialon, Grégoire, Scialom, Thomas

  2. BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games ↗

    Paglieri, Davide, Cupiał, Bartłomiej, Coward, Samuel, Piterbarg, Ulyana, Wolczyk, Maciej, Khan, Akbir et al. · 2024

    All 13 authors

    Paglieri, Davide, Cupiał, Bartłomiej, Coward, Samuel, Piterbarg, Ulyana, Wolczyk, Maciej, Khan, Akbir, Pignatelli, Eduardo, Kuciński, Łukasz, Pinto, Lerrel, Fergus, Rob, Foerster, Jakob Nicolaus, Parker-Holder, Jack, Rocktäschel, Tim

  3. FutureSearch Evals ↗

    FutureSearch

  4. ARC-AGI-1 ↗

    Epoch AI

  5. ARC-AGI-2 ↗

    Epoch AI

  6. Chess Puzzles ↗

    Epoch AI

  7. CritPt v1 ↗

    Epoch AI

  8. FrontierMath Tiers 1-3 (v2) ↗

    Epoch AI

  9. GPQA Diamond ↗

    Epoch AI

  10. Mystery Game Puzzles ↗

    Epoch AI

  11. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

Names used in source tables

GPT-5 (minimal)