RLTasksby ulam.ai
Models / OpenAI

OpenAI / MODEL EVIDENCE

gpt-oss-120b

41 benchmarks · 63 observations · 46 sources · released 2025-08-05

Scores at a glance

41 benchmarks · large dot: gpt-oss-120b; small dots: closest models where reported

LMCA ↗22.14%
2.7868.26

gpt-oss-120b · LMCA · Score · % ↗

DTBench ↗76.27%
41.6598.93

gpt-oss-120b · DTBench · Accuracy · % ↗

Fortress ↗8.24%
5.7874.39

gpt-oss-120b · Scale Labs · Risk elicitation score ↗

GAIA-2 ↗17.9%
7.169.2

GPT-OSS 120B (high) · GAIA-2 · Gaia2 full · Execution pass@1 · baseline ReAct · three runs ↗

7 more reported results

33.1% · GPT-OSS 120B (high) · GAIA-2 · Gaia2 full · Search pass@1 · baseline ReAct · three runs · Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments ↗

8.3% · GPT-OSS 120B (high) · GAIA-2 · Gaia2 full · Ambiguity pass@1 · baseline ReAct · three runs · Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments ↗

10.6% · GPT-OSS 120B (high) · GAIA-2 · Gaia2 full · Adaptability pass@1 · baseline ReAct · three runs · Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments ↗

0.6% · GPT-OSS 120B (high) · GAIA-2 · Gaia2 full · Time pass@1 · baseline ReAct · three runs · Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments ↗

14.6% · GPT-OSS 120B (high) · GAIA-2 · Gaia2 full · Noise pass@1 · baseline ReAct · three runs · Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments ↗

10.6% · GPT-OSS 120B (high) · GAIA-2 · Gaia2 full · Agent2Agent pass@1 · baseline ReAct · three runs · Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments ↗

13.7% · GPT-OSS 120B (high) · GAIA-2 · Gaia2 full · Overall pass@1 · baseline ReAct · three runs · Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments ↗

AlgoTune ↗1.41 ×
1.312.05

gpt-oss-120b (high) · Harmonic-mean speedup ↗

ALE-Bench ↗575.62 Performance points
137.782951.32

gpt-oss-120b · Average contest performance ↗

Closest models by score

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

o3 →OpenAI
20.2 percentile-point gap

14 of 21 shared benchmark comparisons

22.7 percentile-point gap

13 of 21 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. Aider code editing benchmark ↗

    Paul Gauthier, Aider contributors

  2. AIME 2025 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  3. LiveCodeBench Benchmark | Artificial Analysis ↗

    Artificial Analysis

  4. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  5. TextQuests: How Good are LLMs at Text-Based Video Games? — published result table ↗

    Phan, Long, Mazeika, Mantas, Zou, Andy, Hendrycks, Dan · 2025

  6. 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

  7. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  8. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  9. Aider Polyglot ↗

    Epoch AI

  10. Ale Bench — methodology and published results ↗

    Epoch AI · 2026

  11. Algotune — methodology and published results ↗

    Epoch AI · 2026

  12. APEX-Agents ↗

    Epoch AI

  13. CritPt v1 ↗

    Epoch AI

  14. GPQA Diamond ↗

    Epoch AI

  15. Mystery Game Puzzles ↗

    Epoch AI

  16. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  17. SimpleBench ↗

    Epoch AI

  18. Terminal-Bench 2.0 ↗

    Epoch AI

  19. Vending Bench 2 — methodology and published results ↗

    Epoch AI · 2026

  20. WeirdML (v2) ↗

    Epoch AI

  21. AI benchmarks & capabilities ↗

    Epoch AI

  22. Fiction.liveBench — March 14, 2025 benchmark release ↗

    Fiction.live · 2025

  23. Writing benchmark — incorporating mandatory story elements ↗

    lechmazur

  24. WeirdML ↗

    Håvard Tveit Ihle

  25. DistressBench — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  26. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  27. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  28. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  29. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  30. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  31. Measuring AI Ability to Complete Long Software Tasks ↗

    METR

  32. Terminal-Bench 2.0 leaderboard ↗

    Terminal-Bench Team

  33. AIME — evaluation methodology and results ↗

    Vals AI · 2026

  34. CaseLaw — evaluation methodology and results ↗

    Vals AI · 2026

  35. CorpFin — evaluation methodology and results ↗

    Vals AI · 2026

  36. GPQA Diamond — evaluation methodology and results ↗

    Vals AI · 2026

  37. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  38. LegalBench — evaluation methodology and results ↗

    Vals AI · 2026

  39. MATH 500 — evaluation methodology and results ↗

    Vals AI · 2026

  40. MedQA — evaluation methodology and results ↗

    Vals AI · 2026

  41. MGSM — evaluation methodology and results ↗

    Vals AI · 2026

  42. MMLU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  43. Poker Agent — evaluation methodology and results ↗

    Vals AI · 2026

  44. SWE-bench Verified — evaluation methodology and results ↗

    Vals AI · 2026

  45. TaxEval — evaluation methodology and results ↗

    Vals AI · 2026

  46. Surface Evolver Bench ↗

    yhenon

Names used in source tables

GPT OSS 120B · GPT OSS 120B (Mini-SWE-agent) · GPT-OSS 120B · GPT-OSS 120B (high) · GPT-OSS-120b · gpt-oss-120b · gpt-oss-120b (High) · gpt-oss-120b (high) · gpt-oss-120b (low) · gpt-oss-120b (unknown thinking)