Claude Opus 4.7 vs DeepSeek V4.1 Flash: Benchmark Comparison
Claude Opus 4.7 has the higher score on 5 of 12 shared benchmarks; DeepSeek V4.1 Flash leads on 6.
The largest observed score gap is 13.74 pts on Vibe Code Bench v1.1 , where DeepSeek V4.1 Flash leads.
Reported ±1 standard-error ranges overlap on 6 of 12 shared benchmarks with comparable uncertainty data. This is not a pairwise statistical significance test.
Shared benchmark results
Scores and reported standard errors come from the latest visible Vals benchmark version available for both models.
| Benchmark | Claude Opus 4.7 | DeepSeek V4.1 Flash | Gap | Reported uncertainty |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | 6.67% ±2.00 | 6.67% ±1.83 | 0.00 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 38.46% ±3.38 | 41.35% ±3.42 | 2.88 pts | Reported ±1 SE ranges overlap |
| LegalBench | 85.25% ±0.45 | 83.28% ±0.46 | 1.97 pts | Reported ±1 SE ranges do not overlap |
| EMB | 63.73% ±3.11 | 57.21% ±3.23 | 6.52 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 51.51% ±0.49 | 53.48% ±0.39 | 1.97 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 63.86% ±3.14 | 62.46% ±3.15 | 1.41 pts | Reported ±1 SE ranges overlap |
| MedCode | 54.86% ±2.21 | 41.17% ±2.04 | 13.68 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 82.95% ±1.98 | 85.50% ±1.92 | 2.55 pts | Reported ±1 SE ranges overlap |
| SAGE | 56.10% ±3.37 | 47.88% ±3.44 | 8.22 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 43.88% ±4.22 | 45.62% ±4.29 | 1.74 pts | Reported ±1 SE ranges overlap |
| ProgramBench | 0.00% ±0.00 | 0.50% ±0.50 | 0.50 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 71.00% ±4.51 | 84.74% ±2.89 | 13.74 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Claude Opus 4.7 average | DeepSeek V4.1 Flash average |
|---|---|---|
| Legal | 43.46% | 43.76% |
| Finance | 59.70% | 57.72% |
| Healthcare | 68.91% | 63.34% |
| Education | 56.10% | 47.88% |
| Coding | 38.29% | 43.62% |
Cost and latency
Cost per test appears only where the benchmark reports it for both models. Latency is the measured completion time for that benchmark.
| Benchmark | Claude Opus 4.7 cost | DeepSeek V4.1 Flash cost | Claude Opus 4.7 latency | DeepSeek V4.1 Flash latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $10.81 | $0.17 | 24m44s | 9m39s |
| Legal Research Bench | $3.06 | $0.25 | 8m32s | 11m42s |
| LegalBench | N/A | N/A | 26.62s | 6.53s |
| EMB | $12.76 | $0.23 | 38m36s | 13m00s |
| Finance Agent (v2) | $4.03 | $0.21 | 6m00s | 6m04s |
| Tax Agent Bench | $1.27 | $0.13 | 4m39s | 5m49s |
| MedCode | N/A | N/A | 54.25s | 35.13s |
| MedScribe | N/A | N/A | 67.50s | 53.83s |
| SAGE | N/A | N/A | 2m05s | 35.78s |
| Code Migration | $36.39 | $0.94 | 1h12m | 1h45m |
| ProgramBench | N/A | N/A | 54m07s | 1h02m |
| Vibe Code Bench v1.1 | $21.41 | $0.41 | 35m42s | 15m28s |
Results available only for Claude Opus 4.7
- Vals RSI Index
- MortgageTax
- TaxEval v2
- GPQA Diamond
- MMLU Pro
- MMMU Pro
- LiveCodeBench
- SWE-bench
Results available only for DeepSeek V4.1 Flash
- Vals Index
- ProofBench v1.1
- BioMysteryBench
- MysteryMechanism
- Terminal-Bench Science
- IOI
- SkillsBench
- Terminal-Bench 4.0
- Vibe Code Bench 1-100
- CyberBench v1.1
- SRE Bench
- Public Benefits Bench v1.1