Shared benchmarks

16
Shared benchmarks for Gemini 3 Pro and Gemini 3.1 Pro
BenchmarkGemini 3 ProGemini 3.1 Pro
  • 91.9%
  • 94.3%
Evaluation details for GPQA Diamond

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Gemini 3 Pro

Record for Gemini 3 Pro on Graduate-Level Google-Proof Q&A Diamond

Gemini 3.1 Pro

Record for Gemini 3.1 Pro on Graduate-Level Google-Proof Q&A Diamond
  • 92.6%
  • 94.4%high
  • 94.1%
Evaluation details for GPQA Diamond — Epoch AI harness

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Gemini 3 Pro

Record for Gemini 3 Pro on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness

Gemini 3.1 Pro

Record for Gemini 3.1 Pro on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness
  • 91.7%
  • 95.5%
Evaluation details for GPQA Diamond — Vals AI harness

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Gemini 3 Pro

Record for Gemini 3 Pro on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness

Gemini 3.1 Pro

Record for Gemini 3.1 Pro on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness
  • 37.5%
  • 44.4%
Evaluation details for Humanity's Last Exam Full set — No tools

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Gemini 3 Pro

Record for Gemini 3 Pro on Humanity's Last Exam Full set — No tools

Gemini 3.1 Pro

Record for Gemini 3.1 Pro on Humanity's Last Exam Full set — No tools
  • 37.5%
  • 46.4%
Evaluation details for Humanity's Last Exam Full set — Scale AI evaluation

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Gemini 3 Pro

Gemini 3.1 Pro

  • 37.7%
  • 47.3%
Evaluation details for Humanity's Last Exam Text only — Scale AI evaluation

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Gemini 3 Pro

Gemini 3.1 Pro

  • 70.3%
  • 78.2%
Evaluation details for MCP Atlas Public, April 2026 update

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Gemini 3 Pro

Record for Gemini 3 Pro on MCP Atlas Public, April 2026 update

Gemini 3.1 Pro

Record for Gemini 3.1 Pro on MCP Atlas Public, April 2026 update
  • 90.1%
  • 91.0%
Evaluation details for MMLU-Pro Original — Vals AI harness

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Gemini 3 Pro

Record for Gemini 3 Pro on MMLU-Pro Original — Vals AI harness

Gemini 3.1 Pro

  • 81.0%
  • 80.5%
Evaluation details for MMMU-Pro No tools

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Gemini 3 Pro

Record for Gemini 3 Pro on MMMU-Pro No tools

Gemini 3.1 Pro

Record for Gemini 3.1 Pro on MMMU-Pro No tools
  • 87.5%
  • 88.2%
Evaluation details for MMMU-Pro Vals AI harness

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Gemini 3 Pro

Record for Gemini 3 Pro on MMMU-Pro Vals AI harness

Gemini 3.1 Pro

Record for Gemini 3.1 Pro on MMMU-Pro Vals AI harness
  • 76.2%
  • 80.6%
Evaluation details for SWE-bench Verified

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Gemini 3 Pro

Record for Gemini 3 Pro on SWE-bench Verified

Gemini 3.1 Pro

Record for Gemini 3.1 Pro on SWE-bench Verified
  • 76.4%
  • 78.8%
Evaluation details for SWE-bench Verified — Vals AI mini-swe-agent

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Gemini 3 Pro

Gemini 3.1 Pro

  • 54.2%
  • 68.5%
Evaluation details for Terminal-Bench 2.0

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Gemini 3 Pro

Record for Gemini 3 Pro on Terminal-Bench 2.0

Gemini 3.1 Pro

Record for Gemini 3.1 Pro on Terminal-Bench 2.0
  • 55.1%
  • 67.4%
Evaluation details for Terminal-Bench 2.0 — Vals AI Terminus 2

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Gemini 3 Pro

Record for Gemini 3 Pro on Terminal-Bench 2.0 — Vals AI Terminus 2

Gemini 3.1 Pro

Record for Gemini 3.1 Pro on Terminal-Bench 2.0 — Vals AI Terminus 2
  • 36.4%
  • 48.8%
Evaluation details for Toolathlon Original

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Gemini 3 Pro

Record for Gemini 3 Pro on Toolathlon Original

Gemini 3.1 Pro

Record for Gemini 3.1 Pro on Toolathlon Original
  • 14.3%
  • 32.0%
Evaluation details for Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.