Claude Opus 4.8 vs DeepSeek V4.1 Flash 1017: Benchmark Comparison
Claude Opus 4.8 has the higher score on 3 of 9 shared benchmarks; DeepSeek V4.1 Flash 1017 leads on 6.
The largest observed score gap is 14.35 pts on Tax Agent Bench , where DeepSeek V4.1 Flash 1017 leads.
Reported ±1 standard-error ranges overlap on 5 of 9 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 4.8 | DeepSeek V4.1 Flash 1017 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 55.10% ±1.01 | 56.58% ±1.27 | 1.48 pts | Reported ±1 SE ranges overlap |
| Harvey's Legal Agent Benchmark | 9.58% ±2.15 | 9.17% ±2.51 | 0.42 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 43.75% ±3.45 | 45.19% ±3.46 | 1.44 pts | Reported ±1 SE ranges overlap |
| EMB | 69.37% ±2.61 | 61.80% ±3.19 | 7.57 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 53.92% ±0.16 | 56.96% ±2.05 | 3.04 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 30.00% ±3.30 | 44.35% ±3.57 | 14.35 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 47.25% ±4.18 | 44.21% ±4.46 | 3.04 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench 4.0 | 23.23% ±1.34 | 31.82% ±2.62 | 8.59 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 82.72% ±3.08 | 87.73% ±2.75 | 5.01 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | Claude Opus 4.8 average | DeepSeek V4.1 Flash 1017 average |
|---|---|---|
| Legal | 26.67% | 27.18% |
| Finance | 51.10% | 54.37% |
| Coding | 51.07% | 54.59% |
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 4.8 cost | DeepSeek V4.1 Flash 1017 cost | Claude Opus 4.8 latency | DeepSeek V4.1 Flash 1017 latency |
|---|---|---|---|---|
| Vals Index | $13.14 | $0.64 | 39m48s | 36m33s |
| Harvey's Legal Agent Benchmark | $10.22 | $0.54 | 24m08s | 21m39s |
| Legal Research Bench | $2.82 | $0.70 | 11m54s | 35m07s |
| EMB | $12.06 | $0.36 | 43m52s | 16m47s |
| Finance Agent (v2) | $4.22 | $0.46 | 9m07s | 14m39s |
| Tax Agent Bench | $1.69 | $0.46 | 7m59s | 21m04s |
| Code Migration | $30.51 | $1.86 | 1h15m | 2h11m |
| Terminal-Bench 4.0 | $17.14 | $0.54 | 1h11m | 41m10s |
| Vibe Code Bench v1.1 | $26.88 | $0.58 | 1h16m | 16m14s |
Results available only for Claude Opus 4.8
- Vals RSI Index
- LegalBench
- MortgageTax
- TaxEval v2
- MedCode
- MedScribe
- Terminal-Bench-Science
- GPQA Diamond
- MMLU Pro
- MMMU Pro
- SAGE
- LiveCodeBench
- ProgramBench
- SkillsBench
- SWE-bench
- Public Benefits Bench v1.1
- Time Horizon Index: KSP
Results available only for DeepSeek V4.1 Flash 1017
None.