RLTasksby ulam.ai
Models / Google

Google / MODEL EVIDENCE

Gemini 3.1 Pro Preview

55 benchmarks · 74 observations · 57 sources · released 2026-02-19

Scores at a glance

55 benchmarks · large dot: Gemini 3.1 Pro Preview; small dots: closest models where reported

MMMU-Pro ↗82.43%
73.4787.69

Gemini 3.1 Pro Preview · MMMU-Pro · AA implementation ↗

IFBench ↗77.14%
75.5883.33

Gemini 3.1 Pro Preview · IFBench · AA implementation ↗

Chess Puzzles ↗51%
076

Gemini 3.1 Pro Preview · Chess Puzzles · Best score (across scorers) · % ↗

MirrorCode ↗8.89%
8.8977.4

Gemini 3.1 Pro Preview · MirrorCode · Best score (across scorers) · % ↗

BALROG ↗57%
3.768.3

Gemini 3.1 Pro Preview · Balrog · Average progress · % ↗

1 more reported result

56.9% · Gemini 3.1 Pro Preview · Balrog · Average progress · % · Epoch AI · Balrog ↗

GSO ↗22.55%
9.888.24

Gemini 3.1 Pro Preview · GSO-Bench · Score OPT@1 · % ↗

SimpleBench ↗79.6%
45.880.6

Gemini 3.1 Pro Preview · SimpleBench · Score (AVG@5) · % ↗

Terminal-Bench 2.0 ↗80.22%
3.0784.72

Gemini 3.1 Pro Preview · Terminal Bench · Accuracy mean · % ↗

4 more reported results

78.4% · Gemini 3.1 Pro Preview · Terminal Bench · Accuracy mean · % · Epoch AI · Terminal Bench ↗

74.83% · Gemini 3.1 Pro Preview · Terminal Bench · Accuracy mean · % · Epoch AI · Terminal Bench ↗

61.42% · Gemini 3.1 Pro Preview · Terminal Bench · Accuracy mean · % · Epoch AI · Terminal Bench ↗

78.4% · Gemini 3.1 Pro Preview · Terminal Bench · Accuracy mean · % · Epoch AI · Terminal Bench ↗

GBAEval ↗0.85%
0.850.85

Gemini 3.1 Pro Preview · GBAEval · Overall score · % ↗

CritPt ↗17.71%
032.29

Gemini 3.1 Pro Preview · CritPt · Accuracy · % ↗

CL-bench ↗20.8%
11.427.9

Gemini 3.1 Pro Preview · CL-bench · Overall · % ↗

GDP.pdf ↗17%
1717

Gemini 3.1 Pro Preview · GDP.pdf · GDP.pdf score · % ↗

SciCode ↗58.68%
1.2766.9

Gemini 3.1 Pro Preview · SciCode · Score · % ↗

EnigmaEval ↗36.78%
0.3839.28

Gemini 3.1 Pro Preview · EnigmaEval · Accuracy · % ↗

MCP Atlas ↗78.20%
40.288.1

gemini-3.1-pro-preview (high) · Scale Labs · Score ↗

Fortress ↗29.76%
5.7874.39

gemini-3.1-pro-preview · Scale Labs · Risk elicitation score ↗

AlgoTune ↗2.02 ×
1.312.05

Gemini 3.1 Pro Preview (high) · Harmonic-mean speedup ↗

ForecastBench ↗64.3 Brier index
46.467

gemini-3.1-pro-preview† · Overall difficulty-adjusted Brier index ↗

Closest models by score

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

23.5 percentile-point gap

17 of 24 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. Blueprint-Bench 2 | Andon Labs ↗

    Andon Labs

  2. ARC Prize - Leaderboard ↗

    ARC Prize Foundation

  3. Arena leaderboard — WebDev evaluation ↗

    Arena

  4. APEX-Agents-AA Benchmark | Artificial Analysis ↗

    Artificial Analysis

  5. EnterpriseOps-Gym-AA Benchmark | Artificial Analysis ↗

    Artificial Analysis

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

    Artificial Analysis

  7. GPQA Diamond Benchmark | Artificial Analysis ↗

    Artificial Analysis

  8. Harvey LAB-AA v1.1 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  9. IFBench Benchmark | Artificial Analysis ↗

    Artificial Analysis

  10. MMMU-Pro Benchmark | Artificial Analysis ↗

    Artificial Analysis

  11. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  12. 𝜏²-Bench Telecom Benchmark | Artificial Analysis ↗

    Artificial Analysis

  13. Terminal-Bench Hard Benchmark | Artificial Analysis ↗

    Artificial Analysis

  14. OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning — published result table ↗

    Opsahl-Ong, Krista, Singhvi, Arnav, Collins, Jasmine, Zhou, Ivan, Wang, Cindy, Baheti, Ashutosh et al. · 2026

    All 13 authors

    Opsahl-Ong, Krista, Singhvi, Arnav, Collins, Jasmine, Zhou, Ivan, Wang, Cindy, Baheti, Ashutosh, Oertell, Owen, Portes, Jacob, Havens, Sam, Elsen, Erich, Bendersky, Michael, Zaharia, Matei, Chen, Xing

  15. 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

  16. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  17. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  18. DeepSWE ↗

    Datacurve

  19. Algotune — methodology and published results ↗

    Epoch AI · 2026

  20. APEX-Agents ↗

    Epoch AI

  21. ARC-AGI-2 ↗

    Epoch AI

  22. Chess Puzzles ↗

    Epoch AI

  23. CL-bench ↗

    Epoch AI

  24. CL-bench Life ↗

    Epoch AI

  25. CritPt v1 ↗

    Epoch AI

  26. Earthborne Rangers (EBR-bench) ↗

    Epoch AI

  27. ExploitBench v0.1 ↗

    Epoch AI

  28. Forecastbench — methodology and published results ↗

    Epoch AI · 2026

  29. FrontierMath Tier 4 (v1, old) ↗

    Epoch AI

  30. FrontierMath Tier 4 (v2) ↗

    Epoch AI

  31. FrontierMath Tiers 1-3 (v1, old) ↗

    Epoch AI

  32. FrontierMath Tiers 1-3 (v2) ↗

    Epoch AI

  33. Furniture Assembly Benchmark ↗

    Epoch AI

  34. GPQA Diamond ↗

    Epoch AI

  35. Humanity's Last Exam ↗

    Epoch AI

  36. MirrorCode ↗

    Epoch AI

  37. Mystery Game Puzzles ↗

    Epoch AI

  38. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  39. PostTrainBench v1.1 ↗

    Epoch AI

  40. SimpleQA Verified ↗

    Epoch AI

  41. SWE-bench Verified ↗

    Epoch AI

  42. Terminal-Bench 2.0 ↗

    Epoch AI

  43. FutureSearch Evals ↗

    FutureSearch

  44. Gemini 3.1 Pro Preview — GBA Eval ↗

    GBA Eval

  45. GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents ↗

    Shetty, Manish, Jain, Naman, Liu, Jinjian, Kethanaboyina, Vijay, Sen, Koushik, Stoica, Ion · 2025

  46. WeirdML ↗

    Håvard Tveit Ihle

  47. EnigmaEval ↗

    Scale Labs / SEAL

  48. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  49. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  50. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  51. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  52. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  53. AI Model Benchmarks — LM Council ↗

    LM Council

  54. Measuring AI Ability to Complete Long Software Tasks ↗

    METR

  55. GDP.pdf Benchmark | Surge AI ↗

    Surge AI

  56. Terminal-Bench 2.0 leaderboard ↗

    Terminal-Bench Team

  57. ProofBench — evaluation methodology and results ↗

    Vals AI · 2026

Names used in source tables

Gemini 3.1 Pro Preview · Gemini 3.1 Pro Preview (high) · gemini-3.1-pro-preview · gemini-3.1-pro-preview (high) · gemini-3.1-pro-preview†