DeepSeek V4.1 Flash 1017 vs GPT-6.1 Sol: Benchmark Comparison
DeepSeek V4.1 Flash 1017 has the higher score on 4 of 9 shared benchmarks; GPT-6.1 Sol leads on 5.
The largest observed score gap is 23.23 pts on Terminal-Bench 4.0 , where GPT-6.1 Sol leads.
Reported ±1 standard-error ranges overlap on 3 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 | DeepSeek V4.1 Flash 1017 | GPT-6.1 Sol | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 56.58% ±1.27 | 61.15% ±1.01 | 4.57 pts | Reported ±1 SE ranges do not overlap |
| Harvey's Legal Agent Benchmark | 9.17% ±2.51 | 5.42% ±1.75 | 3.75 pts | Reported ±1 SE ranges overlap |
| Legal Research Bench | 45.19% ±3.46 | 38.46% ±3.38 | 6.73 pts | Reported ±1 SE ranges overlap |
| EMB | 61.80% ±3.19 | 70.77% ±2.71 | 8.97 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 56.96% ±2.05 | 52.03% ±0.31 | 4.93 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 44.35% ±3.57 | 21.75% ±2.98 | 22.60 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 44.21% ±4.46 | 65.12% ±4.36 | 20.91 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 31.82% ±2.62 | 55.05% ±1.82 | 23.23 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 87.73% ±2.75 | 88.93% ±1.89 | 1.20 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | DeepSeek V4.1 Flash 1017 average | GPT-6.1 Sol average |
|---|---|---|
| Legal | 27.18% | 21.94% |
| Finance | 54.37% | 48.19% |
| Coding | 54.59% | 69.70% |
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 | DeepSeek V4.1 Flash 1017 cost | GPT-6.1 Sol cost | DeepSeek V4.1 Flash 1017 latency | GPT-6.1 Sol latency |
|---|---|---|---|---|
| Vals Index | $0.64 | $3.24 | 36m33s | 43m10s |
| Harvey's Legal Agent Benchmark | $0.54 | $3.93 | 21m39s | 43m14s |
| Legal Research Bench | $0.70 | $3.38 | 35m07s | 34m20s |
| EMB | $0.36 | $1.14 | 16m47s | 18m28s |
| Finance Agent (v2) | $0.46 | $1.62 | 14m39s | 15m25s |
| Tax Agent Bench | $0.46 | $1.32 | 21m04s | 20m14s |
| Code Migration | $1.86 | $6.51 | 2h11m | 1h36m |
| Terminal-Bench 4.0 | $0.54 | $1.72 | 41m10s | 45m12s |
| Vibe Code Bench v1.1 | $0.58 | $6.23 | 16m14s | 1h15m |
Results available only for DeepSeek V4.1 Flash 1017
None.
Results available only for GPT-6.1 Sol
- Vals RSI Index
- Vals Science Index
- MedCode
- MedScribe
- ProofBench v1.1
- BioMysteryBench
- MysteryMechanism
- Robo-bench
- Terminal-Bench-Science
- SAGE
- IOI
- ProgramBench
- SWE-bench Multimodal
- CyberBench v1.1
- SRE Bench
- Public Benefits Bench v1.1