Claude Opus 4.5 vs DeepSeek V3.2
Head to head on 27 shared benchmarks, with price, context window, and release dates.
Benchmark scores
47evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.5 Anthropic | 62.7% | 61.3% | 1683elo | 73.1 | 20.7% | 81.0% | 13.2% | 83.8% | 43.0% | 83.5% | 78.1% | 79.7% | 74.4% | 62.5% | 81.3% | 90.4% | 80.1% | 73.8% | 88.9% | 36.0% | 47.0% | 70.7% | 79.2% | 74.3% | 40.9% | 20.6% | 86.3% | - | - | 16.7% | - | - | 35.6% | 6.1% | 84.7% | 12.13 | - | 45.2% | 83.2% | 68.7% | 100.0% | 37.4 | 77.5% | 45.0% | 45.3 | 61.8 | - | 62.2% |
| DeepSeek V3.2 DeepSeek | 59.0% | 47.9% | 1511elo | 66.8 | 22.1% | 75.1% | 11.2% | 31.3% | 49.0% | 68.0% | 65.9% | 64.6% | 50.0% | 48.2% | 70.4% | 85.0% | 77.2% | 59.3% | 83.7% | 8.0% | 38.7% | 59.0% | 70.0% | 68.2% | 32.6% | 5.1% | 78.9% | 74.7% | 74.2% | - | 0.0% | 16.0% | - | - | - | - | 57.5% | - | - | - | - | - | - | - | - | - | 65 | 51.7% |
2 / 2 models
| Attribute | Claude Opus 4.5 Anthropic | DeepSeek V3.2 DeepSeek |
|---|---|---|
| Description | Claude Opus 4.5 is an AI model from Anthropic. | DeepSeek V3.2 is an AI model from DeepSeek, released with open weights. |
| Family | Claude | Deepseek |
| Params | - | - |
| Open weights | closed | open |
| License | proprietary | mit |
| Released | 24 Nov 2025 | 1 Dec 2025 |
| Context | 200,000 | 163,840 |
| Input $/1M | $5.00 | $0.28 |
| Output $/1M | $25.00 | $0.42 |
| Cache read $/1M | $0.500 | $0.130 |
| Cache write $/1M | $6.250 | - |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | file, image, text | text |
| Providers | - | - |
| Publisher | Anthropic | DeepSeek |
| Reported scores | Aider Polyglot Benchmark74.2% (Aider) MathArena57.47% GPQA Diamond75.1% (AA) Humanity's Last Exam (HLE)11.2% (AA) |
FAQ
- Is Claude Opus 4.5 or DeepSeek V3.2 better?
- Across the 27 benchmarks both models report on Sophon, Claude Opus 4.5 leads on 25 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Claude Opus 4.5 and DeepSeek V3.2 compare on GPQA Diamond?
- Claude Opus 4.5 scores 81.0% and DeepSeek V3.2 scores 75.1% on GPQA Diamond.
- Which is cheaper, Claude Opus 4.5 or DeepSeek V3.2?
- DeepSeek V3.2 is cheaper at $0.42 per million output tokens against $25.00 for Claude Opus 4.5 - about 59.5x.
- When were Claude Opus 4.5 and DeepSeek V3.2 released?
- Claude Opus 4.5 was released 24 Nov 2025 by Anthropic. DeepSeek V3.2 was released 1 Dec 2025 by DeepSeek.
Comparing something else? Build your own side-by-side.