- Rank
- #43
- Total Output Tokens
- 523,482
- Response Time (avg)
- 32.55s
- Total Cost
- $0.355
DeepSeek V4.1 Flash 1017 (low) vs Muse Ember (high)
Muse Ember (high) leads on average score with 9.2 vs 9.2. Muse Ember (high) has the lower benchmark cost at $0.156 vs $0.355. Muse Ember (high) is faster at 11.67s vs 32.55s, with pass rates of 78.3% vs 79.7%.
Compared models
- Rank
- #36
- Total Output Tokens
- 254,892
- Response Time (avg)
- 11.67s
- Total Cost
- $0.156
Recommended model
Muse Ember (high)
It has the best score here (9.2), while costing about 2.3x less than DeepSeek V4.1 Flash 1017 (low).
Detailed comparison
| Metric | DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017 low | Muse Ember Muse Ember high |
|---|---|---|
| Score | 9.2 | 9.2 |
| Rank | #43 | #36 |
| Reliability | 10.0 | 10.0 |
| Consistency | 9.0 | 9.6 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 78.3% | 79.7% |
| Flaky tests | 3 | 1 |
| Total Runs | 69 | 69 |
| Cost per result | 2.214 | 0.865 |
| Total Cost | $0.355 | $0.156 |
| Input Price | $0.150 / 1M | $0.100 / 1M |
| Output Price | $0.600 / 1M | $0.500 / 1M |
| Cache Read Price | $0.003 / 1M | $0.004 / 1M |
| Cache Write Price | N/A | $0.125 / 1M |
| Total Input Tokens | 267,122 | 282,192 |
| Output Tokens | 7,369 | 14,054 |
| Reasoning Tokens | 516,113 | 240,838 |
| Response Time (avg) | 32.55s | 11.67s |
| Response Time (max) | 443.63s | 53.01s |
| Response Time (total) | 748.62s | 268.45s |
| Parameters | ~748B total (~16B active) | ~150B total (~10B active) |
| Availability | Open source | Closed |
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#43 DeepSeek V4.1 Flash 1017
low- Cost
- $0.006
- Time
- 63.8s
- Tokens
- 11,236 tok
#36 Muse Ember
high- Cost
- $0.005
- Time
- 18.3s
- Tokens
- 9,965 tok
Category Breakdown
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 46.67s | 156,869 | 2,102 | 5,290 | |
| Muse Ember | 10.0 | 10.0 | 100.0% | 0 | 48.28s | 149,560 | 2,625 | 1,759 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 8.3 | 10.0 | 75.0% | 0 | 2.02s | 852 | 171 | 2,193 | |
| Muse Ember | 10.0 | 10.0 | 100.0% | 0 | 2.29s | 798 | 275 | 5,440 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 27.01s | 7,509 | 323 | 45,628 | |
| Muse Ember | 10.0 | 10.0 | 100.0% | 0 | 9.62s | 7,410 | 1,213 | 34,691 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 18.73s | 82,444 | 3,880 | 15,379 | |
| Muse Ember | 10.0 | 10.0 | 100.0% | 0 | 10.86s | 102,312 | 5,879 | 17,216 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 1.71s | 7,446 | 207 | 1,344 | |
| Muse Ember | 10.0 | 10.0 | 100.0% | 0 | 3.86s | 7,215 | 342 | 4,585 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 3.6 | 7.2 | 22.2% | 1 | 174.63s | 909 | 9 | 428,331 | |
| Muse Ember | 5.3 | 10.0 | 33.3% | 0 | 29.08s | 873 | 1,687 | 119,272 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 2.25s | 549 | 116 | 553 | |
| Muse Ember | 10.0 | 10.0 | 100.0% | 0 | 2.80s | 522 | 201 | 1,993 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 1.25s | 783 | 69 | 898 | |
| Muse Ember | 9.8 | 10.0 | 100.0% | 0 | 3.05s | 759 | 159 | 4,867 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 6.9 | 4.9 | 77.8% | 2 | 2.54s | 828 | 236 | 3,620 | |
| Muse Ember | 5.4 | 7.2 | 44.4% | 1 | 12.05s | 786 | 1,091 | 33,034 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 1.92s | 8,672 | 237 | 338 | |
| Muse Ember | 10.0 | 10.0 | 100.0% | 0 | 3.95s | 11,729 | 319 | 1,231 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 3.0 | 10.0 | 0.0% | 0 | 33.79s | 261 | 19 | 12,539 | |
| Muse Ember | 3.0 | 10.0 | 0.0% | 0 | 16.46s | 228 | 263 | 16,750 |
Quick Compare
Switch Comparison Pair
DeepSeek V4.1 Flash 1017lowvsQwen3.8 MAXmediumClaude Sonnet 5.5maxvsDeepSeek V4.1 Flash 1017lowSeed 2.1 TurbolowvsMuse EmberhighDeepSeek V4.1 Flash 1017lowvsGPT-5.5mediumDeepSeek V4.1 Flash 1017lowvsQwen3.8 Max (0902)highDeepSeek V4.1 Flash 1017lowvsMuse WondermediumClaude Opus 5.5mediumvsDeepSeek V4.1 Flash 1017lowDeepSeek V4.1 Flash 1017lowvsGPT-5.3-CodexmediumDeepSeek V4.1 Flash 1017lowvsMuse Spark OpenhighClaude Haiku 5.5xhighvsDeepSeek V4.1 Flash 1017lowClaude Opus 5.5mediumvsMuse EmberhighDeepSeek V4.1 Flash 1017lowvsMuse Spark 1.3high