LogoLMSpeed
Back to models

Model compare

Claude Opus 4.6 vs Gemini 2.5 Pro

The readout for Claude Opus 4.6 and Gemini 2.5 Pro, before the detailed comparison sheet.

Model A

Claude Opus 4.6

Anthropic

Leading
vs

Model B

Gemini 2.5 Pro

Google

Contender

Key Takeaways

Weighted outcome: Claude Opus 4.6. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.

Decision read

Claude Opus 4.6

Claude Opus 4.6 has the higher weighted result; Model A / B score 56 to 44.

Evidence depth

119 data points

Includes 27 benchmark rows, 0 audit samples, and 10 provider examples.

Selection signal

Start with Claude Opus 4.6

The charts below split 37 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 2.5 Pro: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.

Model compare
Claude Opus 4.6
Gemini 2.5 Pro
Overall leaderLeadingContender
Weighted overall score56.0 pts44.0 pts
Benchmark category leads3 categories3 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

TextImageFileAudiovideo

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 2.5 Pro
DeveloperAnthropicGoogle
ReleasedFeb 2026Jun 2025
ParametersNo dataNo data
TokenizerClaudeGemini
Knowledge cutoffNo data2025-01-31
OpenRouter IDanthropic/claude-opus-4.6google/gemini-2.5-pro
ReferencesNo dataNo data

When to choose each model

This report only uses LMSpeed data for Claude Opus 4.6 and Gemini 2.5 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, Coding, Knowledge) and operational dimensions (Cheapest input price, First-token latency, Free providers, Provider coverage).

Gemini 2.5 Pro

Gemini 2.5 Pro is stronger in benchmark categories (Reasoning, Math, Instruction following) 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
6 / 8
Shared
6 shared categories

Avg. score

Claude Opus 4.6

51.8

Avg. score

Gemini 2.5 Pro

45.7

Agents

Claude Opus 4.6 leads by 10.3

Claude Opus 4.654.3
Gemini 2.5 Pro44

Coding

Claude Opus 4.6 leads by 17.8

Claude Opus 4.656.6
Gemini 2.5 Pro38.8

Reasoning

Gemini 2.5 Pro leads by 0.2

Claude Opus 4.653.4
Gemini 2.5 Pro53.6

Knowledge

Claude Opus 4.6 leads by 17.5

Claude Opus 4.653.3
Gemini 2.5 Pro35.8

Math

Gemini 2.5 Pro leads by 0.3

Claude Opus 4.655.7
Gemini 2.5 Pro56

Multilingual

Claude Opus 4.6

Claude Opus 4.648.4
Gemini 2.5 Pro-

Multimodal

Claude Opus 4.6

Claude Opus 4.647.8
Gemini 2.5 Pro-

Instruction following

Gemini 2.5 Pro leads by 1.2

Claude Opus 4.644.8
Gemini 2.5 Pro46

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

winner

62.0

Rank #41/111 · confidence 4 · eval date 2026-02-01

+19.0

Gemini 2.5 Pro

43.0

Rank #103/111 · confidence 1 · eval date 2025-03-01

Pricingverified

Input price

SourceClaude Opus 4.6 (Non-reasoning, High Effort)

Claude Opus 4.6

$5.00/M

Rank #168/186 · confidence 4

+$3.75/M

Gemini 2.5 Pro

winner

$1.25/M

Rank #123/186 · confidence 4

Pricingverified

Blended price

SourceClaude Opus 4.6 (Non-reasoning, High Effort)

Claude Opus 4.6

$10.00/M

Rank #169/186 · confidence 4

+$6.56/M

Gemini 2.5 Pro

winner

$3.44/M

Rank #139/186 · confidence 4

Pricingverified

Output price

SourceClaude Opus 4.6 (Non-reasoning, High Effort)

Claude Opus 4.6

$25.00/M

Rank #169/186 · confidence 4

+$15.00/M

Gemini 2.5 Pro

winner

$10.00/M

Rank #142/186 · confidence 4

Reasoningreported

MMLU-Pro

SourceClaude Opus 4.6

Claude Opus 4.6

82.0%

Rank #50/129 · confidence 4 · eval date 2026-02-01

+4.2%

Gemini 2.5 Pro

winner

86.2%

Rank #18/129 · confidence 4

Reasoningreported

CritPt

SourceClaude Opus 4.6

Claude Opus 4.6

winner

2.8

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

+0.2

Gemini 2.5 Pro

2.6

Rank #58/88 · confidence 1 · eval date 2025-03-01

Reasoningreported

AA-LCR

SourceClaude Opus 4.6

Claude Opus 4.6

winner

67.0

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

+1.0

Gemini 2.5 Pro

66.0

Rank #74/106 · confidence 1 · eval date 2025-03-01

Reasoningverified

GPQA

SourceClaude Opus 4.6 (Non-reasoning, High Effort)

Claude Opus 4.6

84.0%

Rank #75/218 · confidence 4

+0.4%

Gemini 2.5 Pro

winner

84.4%

Rank #71/218 · confidence 4

Reasoningverified

HLE

SourceClaude Opus 4.6 (Non-reasoning, High Effort)

Claude Opus 4.6

19.1%

Rank #89/216 · confidence 4

+3.4%

Gemini 2.5 Pro

winner

22.5%

Rank #77/216 · confidence 4

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

+57.2

Gemini 2.5 Pro

0.4

Rank #33/33 · confidence 1 · eval date 2025-03-01

Codingreported

SWE-bench Verified

SourceClaude Opus 4.6

Claude Opus 4.6

winner

80.8

Rank #8/49 · confidence 4 · eval date 2026-02-01

+17.0

Gemini 2.5 Pro

63.8

Rank #44/49 · confidence 1 · eval date 2025-03-01

Codingreported

AA-SciCode

SourceClaude Opus 4.6

Claude Opus 4.6

winner

45.7

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

+2.9

Gemini 2.5 Pro

42.8

Rank #61/113 · confidence 1 · eval date 2025-03-01

Codingreported

BenchLM Coding score

SourceClaude Opus 4.6

Claude Opus 4.6

winner

50.3

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

+11.6

Gemini 2.5 Pro

38.7

Rank #76/87 · confidence 1 · eval date 2025-03-01

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

+26.6

Gemini 2.5 Pro

14.1

Rank #32/47 · confidence 1 · eval date 2025-03-01

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

+18.7

Gemini 2.5 Pro

4.2

Rank #24/36 · confidence 1 · eval date 2025-03-01

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

+23.3

Gemini 2.5 Pro

35.3

Rank #47/63 · confidence 1 · eval date 2025-03-01

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

+56.3

Gemini 2.5 Pro

23.5

Rank #83/83 · confidence 1 · eval date 2025-03-01

Knowledgereported

AA-Omniscience Hallucination Rate

SourceClaude Opus 4.6

Claude Opus 4.6

80.1

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

+10.8

Gemini 2.5 Pro

winner

90.9

Rank #16/106 · confidence 1 · eval date 2025-03-01

Knowledgereported

AA-Omniscience Accuracy

SourceClaude Opus 4.6

Claude Opus 4.6

winner

45.8

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

+6.7

Gemini 2.5 Pro

39.1

Rank #39/106 · confidence 1 · eval date 2025-03-01

Knowledgereported

Artificial Analysis Intelligence Index

SourceClaude Opus 4.6

Claude Opus 4.6

winner

26.4

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

+0.4

Gemini 2.5 Pro

25.9

Rank #61/117 · confidence 1 · eval date 2025-03-01

Knowledgereported

AA-GPQA Diamond

SourceClaude Opus 4.6

Claude Opus 4.6

84.0

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

+0.4

Gemini 2.5 Pro

winner

84.4

Rank #63/113 · confidence 1 · eval date 2025-03-01

Knowledgereported

AA-HLE

SourceClaude Opus 4.6

Claude Opus 4.6

19.1

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

+3.4

Gemini 2.5 Pro

winner

22.5

Rank #65/114 · confidence 1 · eval date 2025-03-01

Multimodalreported

Design Arena Website

SourceClaude Opus 4.6

Claude Opus 4.6

winner

1306.0

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

+128.0

Gemini 2.5 Pro

1178.0

Rank #58/78 · confidence 1 · eval date 2025-03-01

Multimodalreported

AA-MMMU-Pro

SourceClaude Opus 4.6

Claude Opus 4.6

72.5

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

+2.4

Gemini 2.5 Pro

winner

74.9

Rank #36/68 · confidence 1 · eval date 2025-03-01

Instruction followingreported

AA-IFBench

SourceClaude Opus 4.6

Claude Opus 4.6

44.6

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

+4.1

Gemini 2.5 Pro

winner

48.7

Rank #57/84 · confidence 1 · eval date 2025-03-01

Agentsreported

Gert Labs

SourceClaude Opus 4.6

Claude Opus 4.6

winner

61.9

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

+19.8

Gemini 2.5 Pro

42.0

Rank #33/49 · confidence 1 · eval date 2025-03-01

Agentsreported

τ²-bench results

SourceClaude Opus 4.6

Claude Opus 4.6

winner

84.8

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

+30.7

Gemini 2.5 Pro

54.1

Rank #64/82 · confidence 1 · eval date 2025-03-01

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 2.5 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 2.5 Pro
CatClaw API30 tests

Claude Opus 4.6

speed / latency

N/A / N/A

input / output

No data

Gemini 2.5 Pro

speed / latency

48 tok/s / 23637ms

input / output

No data

Rnglg2 API20 tests

Claude Opus 4.6

speed / latency

57 tok/s / 3926ms

input / output

No data

Gemini 2.5 Pro

speed / latency

111 tok/s / 17899ms

input / output

No data

钠 API20 tests

Claude Opus 4.6

speed / latency

42 tok/s / 2282ms

input / output

No data

Gemini 2.5 Pro

speed / latency

N/A / N/A

input / output

No data

ModelPool15 tests

Claude Opus 4.6

speed / latency

84 tok/s / 3916ms

input / output

No data

Gemini 2.5 Pro

speed / latency

81 tok/s / 21179ms

input / output

No data

N1N10 tests

Claude Opus 4.6

speed / latency

46 tok/s / 2559ms

input / output

No data

Gemini 2.5 Pro

speed / latency

106 tok/s / 16405ms

input / output

No data

Dext API

Claude Opus 4.6

claude-opus-4-6

speed / latency

No data

input / output

$0.240/M/$1.20/M

Gemini 2.5 Pro

gemini-2.5-pro

speed / latency

No data

input / output

$0/M/$0/M

兔子API

Claude Opus 4.6

claude-opus-4-6-low

speed / latency

No data

input / output

$0/request

Gemini 2.5 Pro

gemini-2.5-pro-nothinking

speed / latency

No data

input / output

$0/request

云AI

Claude Opus 4.6

claude-opus-4-6

speed / latency

No data

input / output

$0.123/M/$0.616/M

Gemini 2.5 Pro

gemini-2.5-pro-c

speed / latency

No data

input / output

$0.0010/request

KFCV50

Claude Opus 4.6

claude-opus-4-6

speed / latency

No data

input / output

$0.017/request

Gemini 2.5 Pro

gemini-2.5-pro

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 2.5 Pro

gemini-2.5-pro-c

speed / latency

No data

input / output

$0.0055/request

FAQ

Weighted outcome: Claude Opus 4.6. 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.