LogoLMSpeed
Back to models

Model compare

Claude Opus 4.6 vs Gemini 3.1 Pro

The readout for Claude Opus 4.6 and Gemini 3.1 Pro, before the detailed comparison sheet.

Model A

Claude Opus 4.6

Anthropic

Contender
vs

Model B

Gemini 3.1 Pro

Google

Leading

Key Takeaways

Weighted outcome: Gemini 3.1 Pro. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.

Decision read

Gemini 3.1 Pro

Gemini 3.1 Pro has the higher weighted result; Model A / B score 36 to 64.

Evidence depth

142 data points

Includes 39 benchmark rows, 0 audit samples, and 10 provider examples.

Selection signal

Start with Gemini 3.1 Pro

The charts below split 49 high-signal samples across speed, scores, and audit health.

Change comparison

Switch either side of this report to compare another model with the same LMSpeed data pipeline.

Select a different model to open a new comparison URL.

Comparison sheet

This report only uses LMSpeed data for Claude Opus 4.6 and Gemini 3.1 Pro: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.

Model compare
Claude Opus 4.6
Gemini 3.1 Pro
Overall leaderContenderLeading
Weighted overall score36.0 pts64.0 pts
Benchmark category leads2 categories6 categories
Operational advantagesCheapest input price, First-token latency, Free providers, Provider coverageAverage speed
Context window1M tokens1.0M tokens
Max output128K tokens65.5K tokens
Modalities

Input

TextImageFile

Output

Text

Input

AudioFileImageTextvideo

Output

Text
Features
Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning
Text inputImage inputFile inputAudio inputText outputTool callingStructured outputsJSON modeReasoning

The overall result weights benchmark capability categories at 80% and price, API speed/latency, and availability at 20%. Recent test volume does not affect the winner, and missing benchmark categories are excluded.

Model metadata

Model compare
Claude Opus 4.6
Gemini 3.1 Pro
DeveloperAnthropicGoogle
ReleasedFeb 2026Feb 2026
ParametersNo dataNo data
TokenizerClaudeGemini
Knowledge cutoffNo dataNo data
OpenRouter IDanthropic/claude-opus-4.6google/gemini-3.1-pro-preview
ReferencesNo dataNo data

When to choose each model

This report only uses LMSpeed data for Claude Opus 4.6 and Gemini 3.1 Pro: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.

Claude Opus 4.6

Claude Opus 4.6 is stronger in benchmark categories (Agents, Math) and operational dimensions (Cheapest input price, First-token latency, Free providers, Provider coverage).

Gemini 3.1 Pro

Gemini 3.1 Pro is stronger in benchmark categories (Coding, Reasoning, Knowledge, Multilingual, Multimodal) and operational dimensions (Average speed).

Benchmark score comparison

Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.

Category performance

Compare benchmark category scores on a 0-100 scale. Select a category to inspect the gap.

Model A coverage
8 / 8
Model B coverage
8 / 8
Shared
8 shared categories

Avg. score

Claude Opus 4.6

51.8

Avg. score

Gemini 3.1 Pro

57

Agents

Claude Opus 4.6 leads by 4.1

Claude Opus 4.654.3
Gemini 3.1 Pro50.2

Coding

Gemini 3.1 Pro leads by 0.6

Claude Opus 4.656.6
Gemini 3.1 Pro57.2

Reasoning

Gemini 3.1 Pro leads by 4.0

Claude Opus 4.653.4
Gemini 3.1 Pro57.4

Knowledge

Gemini 3.1 Pro leads by 3.7

Claude Opus 4.653.3
Gemini 3.1 Pro57

Math

Claude Opus 4.6 leads by 1.1

Claude Opus 4.655.7
Gemini 3.1 Pro54.6

Multilingual

Gemini 3.1 Pro leads by 20.9

Claude Opus 4.648.4
Gemini 3.1 Pro69.3

Multimodal

Gemini 3.1 Pro leads by 7.3

Claude Opus 4.647.8
Gemini 3.1 Pro55.1

Instruction following

Gemini 3.1 Pro leads by 10.5

Claude Opus 4.644.8
Gemini 3.1 Pro55.3

Professional benchmark details

Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.

Aggregatereported

BenchLM overall score

SourceClaude Opus 4.6

Claude Opus 4.6

62.0

Rank #42/112 · confidence 4 · eval date 2026-02-01

+5.0

Gemini 3.1 Pro

winner

67.0

Rank #27/112 · confidence 3 · eval date 2026-02-19

Reasoningreported

AA-LCR

SourceClaude Opus 4.6

Claude Opus 4.6

67.0

Rank #71/106 · confidence 4 · eval date 2026-02-01

+15.0

Gemini 3.1 Pro

winner

82.0

Rank #14/106 · confidence 3 · eval date 2026-02-19

Reasoningreported

CritPt

SourceClaude Opus 4.6

Claude Opus 4.6

2.8

Rank #57/88 · confidence 4 · eval date 2026-02-01

+14.9

Gemini 3.1 Pro

winner

17.7

Rank #19/88 · confidence 3 · eval date 2026-02-19

Reasoningreported

BenchLM Reasoning score

SourceClaude Opus 4.6

Claude Opus 4.6

winner

67.1

Rank #42/67 · confidence 4 · eval date 2026-02-01

+16.5

Gemini 3.1 Pro

50.6

Rank #60/67 · confidence 3 · eval date 2026-02-19

Codingreported

LiveCodeBench Pro

SourceClaude Opus 4.6

Claude Opus 4.6

70.7

Rank #4/4 · confidence 4 · eval date 2026-02-01

+12.2

Gemini 3.1 Pro

winner

82.9

Rank #2/4 · confidence 3 · eval date 2026-02-19

Codingreported

React Native Evals

SourceClaude Opus 4.6

Claude Opus 4.6

winner

84.1

Rank #3/12 · confidence 4 · eval date 2026-02-01

+5.2

Gemini 3.1 Pro

78.9

Rank #6/12 · confidence 3 · eval date 2026-02-19

Codingreported

Vibe Code Bench

SourceClaude Opus 4.6

Claude Opus 4.6

winner

57.6

Rank #5/33 · confidence 4 · eval date 2026-02-01

+25.5

Gemini 3.1 Pro

32.0

Rank #13/33 · confidence 3 · eval date 2026-02-19

Codingreported

AA-SciCode

SourceClaude Opus 4.6

Claude Opus 4.6

45.7

Rank #54/113 · confidence 4 · eval date 2026-02-01

+13.0

Gemini 3.1 Pro

winner

58.7

Rank #6/113 · confidence 3 · eval date 2026-02-19

Codingreported

BenchLM Coding score

SourceClaude Opus 4.6

Claude Opus 4.6

50.3

Rank #54/87 · confidence 4 · eval date 2026-02-01

+24.0

Gemini 3.1 Pro

winner

74.3

Rank #7/87 · confidence 3 · eval date 2026-02-19

Mathreported

FrontierMath v2 (Tiers 1-3)

SourceClaude Opus 4.6

Claude Opus 4.6

winner

40.7

Rank #10/47 · confidence 4 · eval date 2026-02-01

+3.8

Gemini 3.1 Pro

36.9

Rank #15/47 · confidence 3 · eval date 2026-02-19

Mathreported

FrontierMath v2 (Tier 4)

SourceClaude Opus 4.6

Claude Opus 4.6

winner

22.9

Rank #11/36 · confidence 4 · eval date 2026-02-01

+6.2

Gemini 3.1 Pro

16.7

Rank #14/36 · confidence 3 · eval date 2026-02-19

Mathreported

BenchLM Math score

SourceClaude Opus 4.6

Claude Opus 4.6

winner

58.6

Rank #29/63 · confidence 4 · eval date 2026-02-01

+4.3

Gemini 3.1 Pro

54.3

Rank #35/63 · confidence 3 · eval date 2026-02-19

Knowledgereported

MedXpertQA (Text)

SourceClaude Opus 4.6

Claude Opus 4.6

52.1

Rank #3/4 · confidence 4 · eval date 2026-02-01

+19.4

Gemini 3.1 Pro

winner

71.5

Rank #1/4 · confidence 3 · eval date 2026-02-19

Knowledgereported

GPQA-D

SourceClaude Opus 4.6

Claude Opus 4.6

89.2

Rank #19/32 · confidence 4 · eval date 2026-02-01

+5.1

Gemini 3.1 Pro

winner

94.3

Rank #3/32 · confidence 3 · eval date 2026-02-19

Knowledgereported

AA-GPQA Diamond

SourceClaude Opus 4.6

Claude Opus 4.6

84.0

Rank #67/113 · confidence 4 · eval date 2026-02-01

+10.1

Gemini 3.1 Pro

winner

94.1

Rank #5/113 · confidence 3 · eval date 2026-02-19

Knowledgereported

AA-Omniscience Index

SourceClaude Opus 4.6

Claude Opus 4.6

2.4

Rank #36/45 · confidence 4 · eval date 2026-02-01

+29.5

Gemini 3.1 Pro

winner

31.9

Rank #5/45 · confidence 3 · eval date 2026-02-19

Knowledgereported

HealthBench Hard

SourceClaude Opus 4.6

Claude Opus 4.6

14.8

Rank #8/8 · confidence 4 · eval date 2026-02-01

+5.8

Gemini 3.1 Pro

winner

20.6

Rank #6/8 · confidence 3 · eval date 2026-02-19

Knowledgereported

HLE w/o tools

SourceClaude Opus 4.6

Claude Opus 4.6

40.0

Rank #14/22 · confidence 4 · eval date 2026-02-01

+5.4

Gemini 3.1 Pro

winner

45.4

Rank #6/22 · confidence 3 · eval date 2026-02-19

Knowledgereported

AA-Omniscience Accuracy

SourceClaude Opus 4.6

Claude Opus 4.6

45.8

Rank #23/106 · confidence 4 · eval date 2026-02-01

+9.1

Gemini 3.1 Pro

winner

54.9

Rank #9/106 · confidence 3 · eval date 2026-02-19

Knowledgereported

AA-HLE

SourceClaude Opus 4.6

Claude Opus 4.6

19.1

Rank #74/114 · confidence 4 · eval date 2026-02-01

+27.9

Gemini 3.1 Pro

winner

47.0

Rank #10/114 · confidence 3 · eval date 2026-02-19

Knowledgereported

BenchLM Knowledge score

SourceClaude Opus 4.6

Claude Opus 4.6

winner

79.8

Rank #15/83 · confidence 4 · eval date 2026-02-01

+0.6

Gemini 3.1 Pro

79.2

Rank #20/83 · confidence 3 · eval date 2026-02-19

Knowledgereported

AA-Omniscience Hallucination Rate

SourceClaude Opus 4.6

Claude Opus 4.6

winner

80.1

Rank #43/106 · confidence 4 · eval date 2026-02-01

+29.2

Gemini 3.1 Pro

50.9

Rank #76/106 · confidence 3 · eval date 2026-02-19

Knowledgereported

Artificial Analysis Intelligence Index

SourceClaude Opus 4.6

Claude Opus 4.6

26.4

Rank #57/117 · confidence 4 · eval date 2026-02-01

+4.0

Gemini 3.1 Pro

winner

30.4

Rank #48/117 · confidence 3 · eval date 2026-02-19

Multilingualreported

AA Global-MMLU-Lite

SourceClaude Opus 4.6 (Adaptive)

Claude Opus 4.6

92.2

Rank #3/5 · confidence 1 · eval date 2026-02-01

+1.0

Gemini 3.1 Pro

winner

93.2

Rank #1/5 · confidence 3 · eval date 2026-02-19

Multimodalreported

MedXpertQA (MM)

SourceClaude Opus 4.6

Claude Opus 4.6

64.8

Rank #6/6 · confidence 4 · eval date 2026-02-01

+16.5

Gemini 3.1 Pro

winner

81.3

Rank #1/6 · confidence 3 · eval date 2026-02-19

Multimodalreported

MMMU-Pro

SourceClaude Opus 4.6

Claude Opus 4.6

77.3

Rank #21/31 · confidence 4 · eval date 2026-02-01

+6.6

Gemini 3.1 Pro

winner

83.9

Rank #2/31 · confidence 3 · eval date 2026-02-19

Multimodalreported

ERQA

SourceClaude Opus 4.6

Claude Opus 4.6

51.6

Rank #8/8 · confidence 4 · eval date 2026-02-01

+17.8

Gemini 3.1 Pro

winner

69.4

Rank #3/8 · confidence 3 · eval date 2026-02-19

Multimodalreported

ScreenSpot Pro

SourceClaude Opus 4.6

Claude Opus 4.6

83.1

Rank #6/12 · confidence 4 · eval date 2026-02-01

+1.3

Gemini 3.1 Pro

winner

84.4

Rank #5/12 · confidence 3 · eval date 2026-02-19

Multimodalreported

AA-MMMU-Pro

SourceClaude Opus 4.6

Claude Opus 4.6

72.5

Rank #45/68 · confidence 4 · eval date 2026-02-01

+9.9

Gemini 3.1 Pro

winner

82.4

Rank #8/68 · confidence 3 · eval date 2026-02-19

Multimodalreported

BenchLM Multimodal Grounded score

SourceClaude Opus 4.6

Claude Opus 4.6

59.5

Rank #40/56 · confidence 4 · eval date 2026-02-01

+19.7

Gemini 3.1 Pro

winner

79.2

Rank #14/56 · confidence 3 · eval date 2026-02-19

Multimodalreported

Design Arena Website

SourceClaude Opus 4.6

Claude Opus 4.6

winner

1304.0

Rank #14/78 · confidence 4 · eval date 2026-02-01

+39.0

Gemini 3.1 Pro

1265.0

Rank #32/78 · confidence 3 · eval date 2026-02-19

Instruction followingreported

AA-IFBench

SourceClaude Opus 4.6

Claude Opus 4.6

44.6

Rank #59/84 · confidence 4 · eval date 2026-02-01

+32.5

Gemini 3.1 Pro

winner

77.1

Rank #7/84 · confidence 3 · eval date 2026-02-19

Agentsreported

Claw-Eval

SourceClaude Opus 4.6

Claude Opus 4.6

winner

70.4

Rank #3/27 · confidence 4 · eval date 2026-02-01

+12.6

Gemini 3.1 Pro

57.8

Rank #16/27 · confidence 3 · eval date 2026-02-19

Agentsreported

ResearchClawBench

SourceClaude Opus 4.6

Claude Opus 4.6

winner

19.9

Rank #4/18 · confidence 4 · eval date 2026-02-01

+6.6

Gemini 3.1 Pro

13.3

Rank #17/18 · confidence 3 · eval date 2026-02-19

Agentsreported

APEX-Agents-AA

SourceClaude Opus 4.6 (Adaptive)

Claude Opus 4.6

winner

33.0

Rank #8/23 · confidence 1 · eval date 2026-02-01

+1.0

Gemini 3.1 Pro

32.0

Rank #9/23 · confidence 3 · eval date 2026-02-19

Agentsreported

Gert Labs

SourceClaude Opus 4.6

Claude Opus 4.6

winner

61.9

Rank #10/49 · confidence 4 · eval date 2026-02-01

+5.0

Gemini 3.1 Pro

56.9

Rank #14/49 · confidence 3 · eval date 2026-02-19

Agentsreported

DeepSearchQA

SourceClaude Opus 4.6

Claude Opus 4.6

winner

73.7

Rank #11/14 · confidence 4 · eval date 2026-02-01

+4.0

Gemini 3.1 Pro

69.7

Rank #13/14 · confidence 3 · eval date 2026-02-19

Agentsreported

τ²-bench results

SourceClaude Opus 4.6

Claude Opus 4.6

84.8

Rank #46/82 · confidence 4 · eval date 2026-02-01

+10.8

Gemini 3.1 Pro

winner

95.6

Rank #17/82 · confidence 3 · eval date 2026-02-19

Agentsreported

BenchLM Agentic score

SourceClaude Opus 4.6

Claude Opus 4.6

63.5

Rank #37/77 · confidence 4 · eval date 2026-02-01

+9.3

Gemini 3.1 Pro

winner

72.8

Rank #28/77 · confidence 3 · eval date 2026-02-19

API audit comparison

Latest completed audits from shared providers, with four safety and integrity score groups plus report links.

Provider
Claude Opus 4.6
Gemini 3.1 Pro
No completed audits are available from shared providers yet.

Provider examples

Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.

Provider
Claude Opus 4.6
Gemini 3.1 Pro
钠 API25 tests

Claude Opus 4.6

speed / latency

42 tok/s / 2282ms

input / output

No data

Gemini 3.1 Pro

speed / latency

96 tok/s / 13019ms

input / output

No data

Kunkunout API20 tests

Claude Opus 4.6

speed / latency

40 tok/s / 16141ms

input / output

No data

Gemini 3.1 Pro

speed / latency

N/A / N/A

input / output

No data

Rnglg2 API15 tests

Claude Opus 4.6

speed / latency

57 tok/s / 3926ms

input / output

No data

Gemini 3.1 Pro

speed / latency

N/A / N/A

input / output

No data

TradingBase API15 tests

Claude Opus 4.6

speed / latency

43 tok/s / 1437ms

input / output

No data

Gemini 3.1 Pro

speed / latency

102 tok/s / 12933ms

input / output

No data

小水管 API15 tests

Claude Opus 4.6

speed / latency

45 tok/s / 6167ms

input / output

No data

Gemini 3.1 Pro

speed / latency

101 tok/s / 15025ms

input / output

No data

兔子API

Claude Opus 4.6

claude-opus-4-6

speed / latency

No data

input / output

$0/request

Gemini 3.1 Pro

gemini-3.1-pro-preview

speed / latency

No data

input / output

$0/request

KFCV50

Claude Opus 4.6

claude-opus-4-6

speed / latency

No data

input / output

$0.017/request

Gemini 3.1 Pro

gemini-3.1-pro-preview

speed / latency

No data

input / output

$0.0052/request

PoloAPI

Claude Opus 4.6

claude-opus-4-6-c

speed / latency

No data

input / output

$0.027/request

Gemini 3.1 Pro

gemini-3.1-pro-preview-c

speed / latency

No data

input / output

$0.0055/request

10dian-API

Claude Opus 4.6

anti/claude-opus-4-6-c

speed / latency

No data

input / output

$0.200/request

Gemini 3.1 Pro

r/gemini-3.1-pro-preview-c

speed / latency

No data

input / output

$0.012/request

Leonhard API

Claude Opus 4.6

claude-opus-4.6

speed / latency

No data

input / output

$0.300/M/$1.50/M

Gemini 3.1 Pro

[按量]gemini-3.1-pro

speed / latency

No data

input / output

$0.015/request

FAQ

Weighted outcome: Gemini 3.1 Pro. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.

Why is this comparison indexable?
It has 6 verifiable comparison points, and both models have pricing or benchmark data.
Are missing metrics invented?
No. Metrics without LMSpeed data are omitted from this report.

Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.