DeepSeek V4.1 Flash vs Muse Spark 1.3: Benchmark Comparison
DeepSeek V4.1 Flash has the higher score on 5 of 14 shared benchmarks; Muse Spark 1.3 leads on 8.
The largest observed score gap is 18.04 pts on Code Migration , where DeepSeek V4.1 Flash leads.
Reported ±1 standard-error ranges overlap on 8 of 14 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 | Muse Spark 1.3 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Vals Index | 51.32% ±1.13 | 53.20% ±1.07 | 1.88 pts | Reported ±1 SE ranges overlap |
| Harvey's Legal Agent Benchmark | 6.67% ±1.83 | 22.92% ±3.42 | 16.25 pts | Reported ±1 SE ranges do not overlap |
| Legal Research Bench | 41.35% ±3.42 | 40.87% ±3.42 | 0.48 pts | Reported ±1 SE ranges overlap |
| EMB | 57.21% ±3.23 | 62.71% ±2.96 | 5.50 pts | Reported ±1 SE ranges overlap |
| Finance Agent (v2) | 53.48% ±0.39 | 58.90% ±0.44 | 5.42 pts | Reported ±1 SE ranges do not overlap |
| Tax Agent Bench | 26.63% ±3.14 | 35.97% ±3.42 | 9.34 pts | Reported ±1 SE ranges do not overlap |
| ProofBench v1.1 | 54.00% ±5.01 | 55.00% ±5.00 | 1.00 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench-Science | 0.00% ±0.00 | 4.29% ±2.44 | 4.29 pts | Reported ±1 SE ranges do not overlap |
| Code Migration | 45.62% ±4.29 | 27.58% ±4.07 | 18.04 pts | Reported ±1 SE ranges do not overlap |
| IOI | 40.28% ±2.56 | 43.94% ±1.45 | 3.67 pts | Reported ±1 SE ranges overlap |
| ProgramBench | 0.50% ±0.50 | 0.50% ±0.50 | 0.00 pts | Reported ±1 SE ranges overlap |
| Terminal-Bench 4.0 | 19.70% ±1.75 | 10.61% ±1.75 | 9.09 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 84.74% ±2.89 | 82.86% ±2.90 | 1.88 pts | Reported ±1 SE ranges overlap |
| CyberBench v1.1 | 73.69% ±5.48 | 69.41% ±5.76 | 4.28 pts | Reported ±1 SE ranges overlap |
Performance by category
| Category | DeepSeek V4.1 Flash average | Muse Spark 1.3 average |
|---|---|---|
| Legal | 24.01% | 31.89% |
| Finance | 45.77% | 52.53% |
| Math | 54.00% | 55.00% |
| Science | 0.00% | 4.29% |
| Coding | 38.17% | 33.10% |
| Cyber | 73.69% | 69.41% |
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 cost | Muse Spark 1.3 cost | DeepSeek V4.1 Flash latency | Muse Spark 1.3 latency |
|---|---|---|---|---|
| Vals Index | $0.33 | $3.38 | 27m53s | 32m46s |
| Harvey's Legal Agent Benchmark | $0.17 | $2.76 | 9m39s | 17m04s |
| Legal Research Bench | $0.25 | $0.65 | 11m42s | 8m51s |
| EMB | $0.23 | $3.55 | 13m00s | 22m55s |
| Finance Agent (v2) | $0.21 | $0.74 | 6m04s | 5m42s |
| Tax Agent Bench | $0.13 | $0.32 | 5m49s | 8m25s |
| ProofBench v1.1 | $0.13 | $0.43 | 9m07s | 8m54s |
| Terminal-Bench-Science | $0.47 | $4.41 | 2h57m | 1h08m |
| Code Migration | $0.94 | $4.62 | 1h45m | 1h08m |
| IOI | $0.24 | $2.36 | 18m30s | 29m51s |
| ProgramBench | $0.90 | $11.56 | 1h02m | 1h09m |
| Terminal-Bench 4.0 | $0.50 | $7.04 | 48m22s | 1h59m |
| Vibe Code Bench v1.1 | $0.41 | $2.10 | 15m28s | 12m54s |
| CyberBench v1.1 | $0.07 | $4.26 | 13m50s | 24m53s |
Results available only for DeepSeek V4.1 Flash
- Vals Science Index
- LegalBench
- MedCode
- MedScribe
- BioMysteryBench
- MysteryMechanism
- SAGE
- SkillsBench
- SWE-bench Multimodal
- Vibe Code Bench 1-100
- SRE Bench
- Public Benefits Bench v1.1
Results available only for Muse Spark 1.3
None.