Claude Opus 4.8 vs Gemini 3.1 Pro Preview
Head to head on 38 shared benchmarks, with price, context window, and release dates.
Benchmark scores
52evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 Anthropic | 15.5% | 14.5% | 66.7% | 62.0% | 1281elo | 1840elo | 80.8 | 53.9% | 47.2% | 22.5% | 1890elo | 92.0% | 48.7% | 62.2% | 10.4% | 80.1% | 79.3% | 78.3% | 67.4% | 81.4% | 84.3% | 89.7% | 91.8% | 53.2% | 85.8% | 69.9% | 83.4% | 69.0% | 54.8% | 53.5% | 69.2% | 75.6% | 82.7% | 58.3% | 55.1% | 70.9% | 82.7% | 94.4% | - | 80.4% | - | - | - | 40.0% | 13.4% | - | - | - | 56.9% | - | - | - | 63.1% |
| Gemini 3.1 Pro Preview Google (Alphabet Inc.) | 12.3% | 26.5% | 64.5% | 20.0% | 1142elo | 1491elo | 68.2 | 43.0% | 36.9% | 16.7% | 1314elo | 94.1% | 47.0% | 77.1% | 0.0% | 82.4% | 76.5% | 78.5% | 79.1% | 85.4% | 91.0% | 84.0% | 86.3% | 59.1% | 76.1% | 69.4% | 76.2% | 26.0% | 48.7% | 58.7% | 54.2% | 72.9% | 70.7% | 53.8% | 33.4% | 56.1% | 32.0% | 95.6% | 76.8% | - | 2 | 73.1% | 22.8% | - | - | 42.5% | 93.2% | 15.1% | - | 84.4% | 72.7% | 79.4 | 58.7% |
2 / 2 models
| Attribute | Claude Opus 4.8 Anthropic | Gemini 3.1 Pro Preview Google (Alphabet Inc.) |
|---|---|---|
| Description | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) is an AI model from Anthropic. | Gemini 3.1 Pro Preview is an AI model from Google (Alphabet Inc.). |
| Family | Claude | Gemini |
| Params | - | - |
| Open weights | - | - |
| License | - | - |
| Released | 28 May 2026 | 19 Feb 2026 |
| Context | 1,000,000 | 1,048,576 |
| Input $/1M | $5.00 | $2.00 |
| Output $/1M | $25.00 | $12.00 |
| Cache read $/1M | $0.500 | $0.200 |
| Cache write $/1M | $6.250 | $0.375 |
| Speed | 0 tok/s | 123 tok/s |
| Latency | 0.00 s | 16.70 s |
| Modalities | text, image, file | audio, file, image, text, video |
| Providers | - | - |
| Publisher | Anthropic | Google (Alphabet Inc.) |
| Reported scores | GPQA Diamond94.1% (AA) Humanity's Last Exam (HLE)47.0% (AA) IFBench77.1% (AA) τ²-bench (Tau²-bench)95.6% (AA) Terminal-Bench (Hard)53.8% (AA) |
FAQ
- Is Claude Opus 4.8 or Gemini 3.1 Pro Preview better?
- Across the 38 benchmarks both models report on Sophon, Claude Opus 4.8 leads on 27 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Claude Opus 4.8 and Gemini 3.1 Pro Preview compare on GPQA Diamond?
- Claude Opus 4.8 scores 92.0% and Gemini 3.1 Pro Preview scores 94.1% on GPQA Diamond.
- Which is cheaper, Claude Opus 4.8 or Gemini 3.1 Pro Preview?
- Gemini 3.1 Pro Preview is cheaper at $12.00 per million output tokens against $25.00 for Claude Opus 4.8 - about 2.1x.
- When were Claude Opus 4.8 and Gemini 3.1 Pro Preview released?
- Claude Opus 4.8 was released 28 May 2026 by Anthropic. Gemini 3.1 Pro Preview was released 19 Feb 2026 by Google (Alphabet Inc.).
Other head-to-heads
56Gemini 3.1 Pro Preview vs GPT-5.541 shared evalsClaude Opus 4.8 vs GPT-5.541 shared evalsClaude Fable 5 vs Claude Opus 4.840 shared evalsClaude Fable 5 vs Gemini 3.1 Pro Preview36 shared evalsGemini 3.1 Pro Preview vs GPT-5.434 shared evalsClaude Sonnet 4.6 vs Gemini 3.1 Pro Preview32 shared evalsGemini 3.1 Pro Preview vs GLM 5.132 shared evalsClaude Opus 4.6 vs Gemini 3.1 Pro Preview31 shared evalsClaude Opus 4.7 vs Gemini 3.1 Pro Preview31 shared evalsGemini 3.1 Pro Preview vs Kimi K2.530 shared evalsGemini 3.1 Pro Preview vs GPT-5.4 Mini30 shared evalsClaude Opus 4.7 vs Claude Opus 4.830 shared evalsGemini 3.1 Pro Preview vs GPT-5.229 shared evalsClaude Opus 4.8 vs Claude Sonnet 4.629 shared evalsClaude Opus 4.5 vs Gemini 3.1 Pro Preview28 shared evalsClaude Opus 4.6 vs Claude Opus 4.828 shared evalsClaude Opus 4.8 vs GPT-5.428 shared evalsClaude Opus 4.8 vs Kimi K2.528 shared evalsClaude Sonnet 4.5 vs Gemini 3.1 Pro Preview27 shared evalsGemini 3.1 Pro Preview vs GPT-5 Mini27 shared evalsGemini 3.1 Pro Preview vs Qwen3.6 Plus27 shared evalsClaude Opus 4.8 vs GLM 5.127 shared evalsClaude Opus 4.8 vs GPT-5.226 shared evalsClaude Opus 4.8 vs GPT-5.4 Mini26 shared evalsClaude Opus 4.8 vs Claude Sonnet 4.525 shared evalsGemini 3.1 Pro Preview vs Grok 4.1 Fast25 shared evalsClaude Opus 4.8 vs Qwen3.6 Plus25 shared evalsClaude Opus 4.8 vs GPT-5 Mini24 shared evalsDeepSeek V3.2 vs Gemini 3.1 Pro Preview24 shared evalsClaude Opus 4.5 vs Claude Opus 4.824 shared evalsClaude Opus 4.8 vs Grok 4.1 Fast24 shared evalsClaude 4 Sonnet vs Gemini 3.1 Pro Preview23 shared evalsGemini 3.1 Pro Preview vs GPT-5 Nano22 shared evalsClaude Opus 4.8 vs GPT-5 Nano22 shared evalsClaude 4 Sonnet vs Claude Opus 4.822 shared evalsClaude Opus 4.8 vs DeepSeek V3.222 shared evalsGemini 3.1 Pro Preview vs GLM 4.721 shared evalsClaude Opus 4.8 vs GLM 4.721 shared evalsGemini 2.5 Pro vs Gemini 3.1 Pro Preview20 shared evalsClaude Opus 4.8 vs Gemini 2.5 Pro20 shared evalsGemini 3.1 Pro Preview vs GPT-519 shared evalsClaude Opus 4.8 vs GPT-6 Astra19 shared evalsGemini 3.1 Pro Preview vs gpt-oss-120b18 shared evalsClaude Opus 4.8 vs gpt-oss-120b18 shared evalsClaude Opus 4.8 vs GPT-517 shared evalsGemini 3.1 Pro Preview vs GPT-6 Astra16 shared evalsGemini 3.1 Pro Preview vs GPT-4o14 shared evalsClaude Opus 4.8 vs GPT-4o14 shared evalsGemini 3.1 Pro Preview vs GPT-4.113 shared evalsGemini 3.1 Pro Preview vs GPT-4.1 Mini12 shared evalsGemini 3.1 Pro Preview vs GPT-4o-mini12 shared evalsGemini 3.1 Pro Preview vs GPT-4.1 Nano12 shared evalsClaude Opus 4.8 vs GPT-4o-mini12 shared evalsClaude Opus 4.8 vs GPT-4.1 Nano12 shared evalsClaude Opus 4.8 vs GPT-4.1 Mini11 shared evalsClaude Opus 4.8 vs GPT-4.111 shared evals
Comparing something else? Build your own side-by-side.