Claude Sonnet 4.6 vs Gemini 3.1 Pro: Specs & Benchmark Comparison

CharacteristicClaude Sonnet 4.6Gemini 3.1 Pro
CompanyAnthropicGoogle
Release DateFebruary 17, 2026February 19, 2026
Parameters
MultimodalYesYes
Context (input)200K1.0M
Context (output)64K66K
Input Price / 1M$3.00$2.50
Output Price / 1M$15.00$15.00
Average Score0.70.8
Benchmarks
ARC-AGI v20.60.8
CharXiv-R0.70.9
MMMU-Pro0.80.8
GPQA0.90.9
MMMLU0.90.9
HLE0.50.5
SWE-bench Verified0.80.8

Visual Benchmark Comparison

Claude Sonnet 4.6
Gemini 3.1 Pro
ARC-AGI v20.6 vs 0.8
0.6
0.8
CharXiv-R0.7 vs 0.9
0.7
0.9
MMMU-Pro0.8 vs 0.8
0.8
0.8
GPQA0.9 vs 0.9
0.9
0.9
MMMLU0.9 vs 0.9
0.9
0.9
HLE0.5 vs 0.5
0.5
0.5
SWE-bench Verified0.8 vs 0.8
0.8
0.8

Verdict

Gemini 3.1 Pro leads in 2 out of 5 comparison categories.

Overall Performance

Both models show comparable average scores: Claude Sonnet 4.6 — 0.7, Gemini 3.1 Pro — 0.8.

Programming

On SWE-Bench, both models are nearly equal: Claude Sonnet 4.6 — 0.8, Gemini 3.1 Pro — 0.8.

API Cost

Gemini 3.1 Pro is 1.0x cheaper: input $2.50/1M vs $3.00/1M tokens.

Context Window

Gemini 3.1 Pro supports a larger context: 1M vs 200K tokens.

Recency

Both models were released around the same time: 2/17/2026 and 2/19/2026.

More About These Models

Related Comparisons

The Claude Sonnet 4.6 and Gemini 3.1 Pro comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the Claude Sonnet 4.6 or Gemini 3.1 Pro page. See also the complete list of AI model comparisons.