DeepSeek V4.1 Flash 1017 vs Muse Spark 1.3 Max: Benchmark Comparison
DeepSeek V4.1 Flash 1017 has the higher score on 3 of 9 shared benchmarks; Muse Spark 1.3 Max leads on 6.
The largest observed score gap is 14.58 pts on Harvey's Legal Agent Benchmark , where Muse Spark 1.3 Max leads.
Reported ±1 standard-error ranges overlap on 6 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 | Muse Spark 1.3 Max | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 56.58% ±1.27 | 58.16% ±1.19 | 1.58 pts | Reported ±1 SE ranges overlap |
| Harvey's Legal Agent Benchmark | 9.17% ±2.51 | 23.75% ±3.55 | 14.58 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 45.19% ±3.46 | 55.29% ±3.46 | 10.10 pts | Reported ±1 SE ranges do not overlap |
| EMB | 61.80% ±3.19 | 67.43% ±3.06 | 5.62 pts | Reported ±1 SE ranges overlap |
| Finance Agent (v2) | 56.96% ±2.05 | 59.96% ±2.06 | 3.00 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 44.35% ±3.57 | 42.44% ±3.51 | 1.91 pts | Reported ±1 SE ranges overlap |
| Code Migration | 44.21% ±4.46 | 47.41% ±4.26 | 3.20 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench 4.0 | 31.82% ±2.62 | 24.75% ±0.51 | 7.07 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 87.73% ±2.75 | 85.86% ±2.51 | 1.87 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | DeepSeek V4.1 Flash 1017 average | Muse Spark 1.3 Max average |
|---|---|---|
| Legal | 27.18% | 39.52% |
| Finance | 54.37% | 56.61% |
| Coding | 54.59% | 52.67% |
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 | Muse Spark 1.3 Max cost | DeepSeek V4.1 Flash 1017 latency | Muse Spark 1.3 Max latency |
|---|---|---|---|---|
| Vals Index | $0.64 | $3.79 | 36m33s | 23m34s |
| Harvey's Legal Agent Benchmark | $0.54 | $2.26 | 21m39s | 14m43s |
| Legal Research Bench | $0.70 | $0.59 | 35m07s | 5m17s |
| EMB | $0.36 | $2.55 | 16m47s | 13m50s |
| Finance Agent (v2) | $0.46 | $0.76 | 14m39s | 3m19s |
| Tax Agent Bench | $0.46 | $0.39 | 21m04s | 4m09s |
| Code Migration | $1.86 | $14.21 | 2h11m | 1h24m |
| Terminal-Bench 4.0 | $0.54 | $6.65 | 41m10s | 52m56s |
| Vibe Code Bench v1.1 | $0.58 | $2.54 | 16m14s | 16m18s |
Results available only for DeepSeek V4.1 Flash 1017
None.
Results available only for Muse Spark 1.3 Max
- Vals RSI Index
- ProofBench v1.1
- MysteryMechanism
- Terminal-Bench-Science
- IOI
- ProgramBench
- SWE-bench Multimodal
- Vibe Code Bench 1-100
- CyberBench v1.1
- SRE Bench
- CUA-bench