Data points: 149
Model compare
The readout for Claude Sonnet 4.6 and Gemini 3.1 Pro, before the detailed comparison sheet.
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 34.9 to 65.1.
Evidence depth
149 data points
Includes 25 benchmark rows, 6 audit samples, and 7 provider examples.
Selection signal
Start with Gemini 3.1 Pro
The charts below split 38 high-signal samples across speed, scores, and audit health.
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.
This report only uses LMSpeed data for Claude Sonnet 4.6 and Gemini 3.1 Pro: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | Claude Sonnet 4.6 | Gemini 3.1 Pro |
|---|---|---|
| Overall leader | Contender | Leading |
| Weighted overall score | 34.9 pts | 65.1 pts |
| Benchmark category leads | 2 categories | 5 categories |
| Operational advantages | Cheapest input price, First-token latency, Provider coverage | Average speed, Free providers |
| Context window | 1M tokens | 1.0M tokens |
| Max output | 128K tokens | 65.5K tokens |
| Modalities | Input TextImageFile Output Text |
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 compare | Claude Sonnet 4.6 | Gemini 3.1 Pro |
|---|---|---|
| Developer | Anthropic | |
| Released | Feb 2026 | Feb 2026 |
| Parameters | No data | No data |
| Tokenizer | Claude | Gemini |
| Knowledge cutoff | No data | No data |
| OpenRouter ID | anthropic/claude-sonnet-4.6 | google/gemini-3.1-pro-preview |
| References | No data | No data |
This report only uses LMSpeed data for Claude Sonnet 4.6 and Gemini 3.1 Pro: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
Claude Sonnet 4.6
Claude Sonnet 4.6 is stronger in benchmark categories (Agents, Knowledge) and operational dimensions (Cheapest input price, First-token latency, Provider coverage).
Gemini 3.1 Pro
Gemini 3.1 Pro is stronger in benchmark categories (Coding, Reasoning, Math, Multimodal, Instruction following) and operational dimensions (Average speed, Free providers).
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
Compare benchmark category scores on a 0-100 scale. Select a category to inspect the gap.
Avg. score
Claude Sonnet 4.6
53.2
Avg. score
Gemini 3.1 Pro
56.6
Claude Sonnet 4.6 leads by 2.8
Gemini 3.1 Pro leads by 3.1
Gemini 3.1 Pro leads by 8.1
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
Claude Sonnet 4.6
63.0
Rank #28/90 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner71.0
Rank #14/90 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
57.7
Rank #68/94 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner72.7
Rank #13/94 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
0.9
Rank #64/77 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner17.7
Rank #13/77 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
46.9
Rank #36/101 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner58.9
Rank #2/101 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
winner80.6
Rank #5/12 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
78.9
Rank #6/12 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
winner51.5
Rank #7/33 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
32.0
Rank #13/33 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
winner63.7
Rank #9/71 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
61.4
Rank #16/71 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
8.3
Rank #19/35 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner16.7
Rank #13/35 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
32.4
Rank #18/47 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner36.9
Rank #15/47 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
49.5
Rank #32/57 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner55.2
Rank #29/57 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
79.9
Rank #68/101 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner94.1
Rank #1/101 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
38.0
Rank #33/95 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner55.3
Rank #5/95 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
13.2
Rank #68/101 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner44.7
Rank #6/101 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
35.9
Rank #48/104 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner46.5
Rank #17/104 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
winner76.9
Rank #20/60 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
66.8
Rank #34/60 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
winner65.9
Rank #57/95 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
49.9
Rank #71/95 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
70.6
Rank #44/61 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner82.4
Rank #5/61 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
57.5
Rank #29/40 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner81.9
Rank #7/40 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
winner1310.0
Rank #11/69 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
1276.0
Rank #24/69 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
77.4
Rank #19/24 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner80.2
Rank #16/24 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
41.2
Rank #69/86 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner77.1
Rank #10/86 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
winner67.8
Rank #5/28 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
57.8
Rank #17/28 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
winner62.9
Rank #8/50 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
56.9
Rank #14/50 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
79.5
Rank #56/84 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner95.6
Rank #17/84 · confidence 3 · eval date 2026-02-19
Claude Sonnet 4.6
54.7
Rank #35/59 · confidence 3 · eval date 2026-02-01
Gemini 3.1 Pro
winner74.0
Rank #18/59 · confidence 3 · eval date 2026-02-19
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | Claude Sonnet 4.6 | Gemini 3.1 Pro |
|---|---|---|
Winner: Claude Sonnet 4.6 | Claude Sonnet 4.6 claude-sonnet-4-6 Audit score 97 10010086100 | Gemini 3.1 Pro gemini-3.1-pro-preview Audit score 79 698463100 |
Winner: Claude Sonnet 4.6 | Claude Sonnet 4.6 claude-sonnet-4-6 Audit score 94 76100100100 | Gemini 3.1 Pro gemini-3.1-pro-preview No audit yet |
Winner: Claude Sonnet 4.6 | Claude Sonnet 4.6 claude-sonnet-4-6 Audit score 94 76100100100 | Gemini 3.1 Pro gemini-3.1-pro No audit yet |
Winner: Claude Sonnet 4.6 | Claude Sonnet 4.6 claude-sonnet-4-6 Audit score 89 56100100100 | Gemini 3.1 Pro gemini-3.1-pro-preview No audit yet |
Winner: Gemini 3.1 Pro | Claude Sonnet 4.6 claude-sonnet-4-6 No audit yet | Gemini 3.1 Pro gemini-3.1-pro-preview Audit score 87 848480100 |
Winner: Gemini 3.1 Pro | Claude Sonnet 4.6 claude-sonnet-4-6 No audit yet | Gemini 3.1 Pro gemini-3.1-pro-preview Audit score 83 787280100 |
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | Claude Sonnet 4.6 | Gemini 3.1 Pro |
|---|---|---|
25 tests | Claude Sonnet 4.6 speed / latency 32 tok/s / 6074ms input / output No data | Gemini 3.1 Pro speed / latency N/A / N/A input / output No data |
25 tests | Claude Sonnet 4.6 speed / latency 40 tok/s / 3145ms input / output No data | Gemini 3.1 Pro speed / latency N/A / N/A input / output No data |
20 tests | Claude Sonnet 4.6 speed / latency 31 tok/s / 4124ms input / output No data | Gemini 3.1 Pro speed / latency 101 tok/s / 15025ms input / output No data |
15 tests | Claude Sonnet 4.6 speed / latency 48 tok/s / 1587ms input / output No data | Gemini 3.1 Pro speed / latency 98 tok/s / 12325ms input / output No data |
10 tests | Claude Sonnet 4.6 speed / latency N/A / N/A input / output No data | Gemini 3.1 Pro speed / latency 121 tok/s / 11404ms input / output No data |
Claude Sonnet 4.6 claude-sonnet-4-6 speed / latency No data input / output $0/M/$0/M | Gemini 3.1 Pro gemini-3.1-pro-preview speed / latency No data input / output $0/M | |
Claude Sonnet 4.6 claude-sonnet-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 |
Weighted outcome: Gemini 3.1 Pro. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Input
Output
| Features | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning | Text inputImage inputFile inputAudio inputText outputTool callingStructured outputsJSON modeReasoning |
|---|
Claude Sonnet 4.6 leads by 12.8
Gemini 3.1 Pro leads by 2.1
Gemini 3.1 Pro
Gemini 3.1 Pro leads by 11.5
Gemini 3.1 Pro leads by 11.8
