Gemini 3.1 Pro

Gemini 3.1 Pro is a reasoning model from Google. 37 benchmarks count toward its score, in 7 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.64.7 ±3.2
CoverageShare of the index weight with results.95%
SpeedOutput tokens per second.115/s
Input / 1MUS dollars per 1M input tokens.$2
Output / 1MUS dollars per 1M output tokens.$12
ContextMaximum tokens in one request.1M
EloLMArena rating and rank.N/A

The index is a score out of 100. The ± range shows how much it can change.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
55.9
CodingCode writing and repair.
64.5
ReasoningLogic problems and puzzles.
69.2
MultimodalTasks with images and text.
64.1
KnowledgeFacts and expert knowledge.
70.2
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
67.3
MathMath problems.
63.5

Results

37 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
τ²-Bench Tool-Agent-User EvaluationAgentic95.6%67.4Victor Barres et al.
OTIS Mock AIME 2024-2025Math95.6%65.0high effortEpoch AI
GPQA diamondKnowledge94.4%65.4high effortEpoch AI
GPQA DiamondKnowledge94.3%65.3David Rein et al.
Artificial Analysis GPQA DiamondKnowledge94.1%65.0Artificial Analysis
Artificial Analysis Global-MMLU-LiteMultilingual93.2%Artificial Analysis
ScreenSpot ProMultimodal84.4%66.4Kaixin Li et al.
Massive Multi-discipline Multimodal Understanding ProMultimodal83.9%63.9MMMU-Pro authors
LiveCodeBench ProCoding82.9%LiveCodeBench Pro authors
Artificial Analysis MMMU-ProMultimodal82.4%67.8Artificial Analysis
Artificial Analysis Long Context ReasoningReasoning82.0%65.0Artificial Analysis
MedXpertQA MultimodalMultimodal81.3%Meta AI
CharXiv ReasoningMultimodal80.2%57.4CharXiv authors
React Native EvalsCoding78.9%57.9Callstack
Artificial Analysis IFBenchInstruction77.1%67.3Artificial Analysis
SWE-Bench verifiedCoding75.6%58.2Epoch AI
SimpleQA VerifiedKnowledge73.5%89.6high effortEpoch AI
SimpleVQAMultimodal72.4%65.1Z.AI
MedXpertQA TextKnowledge71.5%Meta AI
DeepSearchQAAgentic69.7%53.3Meta AI
ERQAMultimodal69.4%63.8Qwen
Artificial Analysis Coding IndexCoding68.8%67.5Artificial Analysis
FrontierMath-Tiers-1-3-v2-PrivateMath59.6%65.0Epoch AI
Artificial Analysis SciCodeCoding58.7%74.3Artificial Analysis
Claw-EvalAgentic57.8%49.3Bowen Ye et al.
Gert Labs Composite Game BenchmarkAgentic56.9%62.9Gert Labs
Artificial Analysis Omniscience AccuracyKnowledge54.9%81.8Artificial Analysis
Chess PuzzlesReasoning49.0%86.9high effortEpoch AI
Artificial Analysis Humanity's Last ExamKnowledge47.0%75.5Artificial Analysis
Humanity's Last Exam without toolsKnowledge45.4%67.2OpenAI
FrontierMath-2025-02-28-PrivateMath36.9%65.0Epoch AI
Mystery Game PuzzlesReasoning34.0%70.1high effortEpoch AI
APEX-Agents-AAAgentic32.0%66.3Artificial Analysis / Mercor
Artificial Analysis Intelligence IndexKnowledge29.7%59.6Artificial Analysis
ZeroBenchMultimodal29.0%Meta AI
FrontierMath-Tier-4-v2-PrivateMath26.8%60.8Epoch AI
Furniture AssemblyReasoning26.7%58.5high effortEpoch AI
HealthBench HardKnowledge20.6%57.4Meta AI
Critical Physics TasksReasoning17.7%75.5Artificial Analysis
FrontierMath-Tier-4-2025-07-01-PrivateMath16.7%61.6Epoch AI
EBR-benchReasoning14.3%59.1Epoch AI
GDPval-AA normalizedAgentic13.8%46.2Artificial Analysis
ResearchClawBenchAgentic13.3%InternScience
Artificial Analysis Agentic IndexAgentic10.3%45.6Artificial Analysis
MirrorCodeCoding8.9%high effortEpoch AI

37 benchmarks count, from 38 of 45 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsEpoch AI, collected directlyCC BY — free to use and redistribute with attribution

Same level, lower price

Qwen3.8-Flash-Next66.4 · Freedots3-note Preview65.5 · FreeDeepSeek V4 Flash 042363.0 · $0.177

More from Google

Gemini 3.7 Flash72.3Gemini 3.8 Flash72.1Gemini 3.5 Flash67.3Gemini 3.6 Flash66.8Gemini 3 Pro60.5