Model comparison
Gemini 3.1 Pro vs Claude Opus 4.6
- Input
- $2.00
- Output
- $12.00
- Context
- 1M
- Released
- 2026-02-19
- Input
- $5 / 1M tokens
- Output
- $25 / 1M tokens
- Context
- 1M
- Released
- 2026-02-05
Gemini 3.1 Pro scores higher on 4 of the 5 benchmarks both models report (the other leads on 1); Gemini 3.1 Pro is cheaper on input tokens ($2 vs $5 per 1M, 2.5×).
Specs and pricing side by side
| Spec | Gemini 3.1 Pro | Claude Opus 4.6 |
|---|---|---|
| Maker | Anthropic | |
| Released | 2026-02-19 | 2026-02-05 |
| Context window | 1M | 1Msame |
| Max output | 64K | 128K (up to 300K via batch beta) |
| Input price | $2.00 | $5 / 1M tokens |
| Output price | $12.00 | $25 / 1M tokens |
| Parameters | Undisclosed | Undisclosedsame |
| License | Proprietary | Proprietary (commercial, usage-based API) |
| Weights | API only | API onlysame |
| Modalities | Text, Vision, Audio, Video, PDF | Text, Vision, PDF |
| Knowledge cutoff | January 2025 | Reliable knowledge cutoff May 2025; training… |
Benchmarks both models report
| Benchmark | Gemini 3.1 Pro | Claude Opus 4.6 |
|---|---|---|
| ARC-AGI-2 | 77.1% | 68.8% |
| SWE-Bench Verified | 80.6% | 79.8% |
| MRCR v2 | 84.9% | 76% |
| Humanity's Last Exam | 44.4% | 53% |
| Terminal-Bench 2.0 | 68.5% | 65.4% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick Gemini 3.1 Pro if…
- You care about ARC-AGI-2, SWE-Bench Verified, MRCR v2 (it scores higher on 4 shared benchmarks).
- Cost matters: input tokens cost 2.5× less ($2 vs $5 per 1M).
- You need Audio / Video input, which Claude Opus 4.6 lacks.
- Your use case is: agentic workflows and multi-step tool use.
Pick Claude Opus 4.6 if…
- You care about Humanity's Last Exam (it scores higher on 1 shared benchmark).
- Your use case is: autonomous and agentic coding workflows (multi-step tasks, terminal/CLI agents).
FAQ
Which is better, Gemini 3.1 Pro or Claude Opus 4.6?
Gemini 3.1 Pro scores higher on 4 of the 5 benchmarks both models report (the other leads on 1); Gemini 3.1 Pro is cheaper on input tokens ($2 vs $5 per 1M, 2.5×). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is Gemini 3.1 Pro?
Gemini 3.1 Pro: $2.00 input, $12.00 output. Claude Opus 4.6: $5 / 1M tokens input, $25 / 1M tokens output (list API prices as published by each maker).
What are the context windows of Gemini 3.1 Pro and Claude Opus 4.6?
Gemini 3.1 Pro offers 1M with up to 64K output; Claude Opus 4.6 offers 1M with up to 128K (up to 300K via batch beta) output.
Is Gemini 3.1 Pro newer than Claude Opus 4.6?
Gemini 3.1 Pro was released 2026-02-19; Claude Opus 4.6 was released 2026-02-05.
Go deeper
- Gemini 3.1 Pro: full specs, pricing and benchmarks
- Claude Opus 4.6: full specs, pricing and benchmarks
- gemini 3 1 pro vs gemini 3 pro
- claude opus 4 7 vs claude opus 4 6
- qwen3 7 max vs gemini 3 1 pro
- claude opus 4 6 vs claude opus 4 5
- claude opus 4 7 vs gemini 3 1 pro
- muse spark vs claude opus 4 6
- All model comparisons