- Rank
- #90
- Total Output Tokens
- 371,547
- Response Time (avg)
- 28.04s
- Total Cost
- $0.153
DeepSeek V4.1 Flash (low) vs GPT-5.4 Mini (medium)
DeepSeek V4.1 Flash (low) leads on average score with 8.0 vs 7.9. DeepSeek V4.1 Flash (low) has the lower benchmark cost at $0.153 vs $1.008. DeepSeek V4.1 Flash (low) is faster at 28.04s vs 29.94s, with pass rates of 73.9% vs 69.6%.
Compared models
- Rank
- #99
- Total Output Tokens
- 184,172
- Response Time (avg)
- 29.94s
- Total Cost
- $1.008
Recommended model
DeepSeek V4.1 Flash (low)
It has the best score here (8.0), while costing about 6.6x less than GPT-5.4 Mini (medium).
Detailed comparison
| Metric | DeepSeek V4.1 Flash DeepSeek V4.1 Flash low | GPT-5.4 Mini GPT-5.4 Mini medium |
|---|---|---|
| Score | 8.0 | 7.9 |
| Rank | #90 | #99 |
| Reliability | 9.6 | 10.0 |
| Consistency | 8.7 | 8.2 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 73.9% | 69.6% |
| Flaky tests | 4 | 5 |
| Total Runs | 69 | 69 |
| Cost per result | 1.576 | 7.754 |
| Total Cost | $0.153 | $1.008 |
| Input Price | $0.020 / 1M | $0.750 / 1M |
| Output Price | $0.396 / 1M | $4.500 / 1M |
| Total Input Tokens | 266,849 | 238,925 |
| Output Tokens | 8,284 | 7,109 |
| Reasoning Tokens | 363,263 | 177,063 |
| Response Time (avg) | 28.04s | 29.94s |
| Response Time (max) | 149.84s | 138.75s |
| Response Time (total) | 645.03s | 688.57s |
| Parameters | 748B total (16B active) | ~400B total (~17B active) |
| Availability | Open source | Closed |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#90 DeepSeek V4.1 Flash
low- Cost
- $0.017
- Time
- 43.6s
- Tokens
- 14,069 tok
#99 GPT-5.4 Mini
medium- Cost
- $0.056
- Time
- 95.5s
- Tokens
- 12,464 tok
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
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 | 6.1 | 3.1 | 66.7% | 1 | 56.02s | 167,134 | 1,903 | 21,681 | |
| GPT-5.4 Mini | 10.0 | 10.0 | 100.0% | 0 | 100.66s | 141,761 | 898 | 24,930 |
| 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 | 8.3 | 10.0 | 75.0% | 0 | 3.32s | 852 | 171 | 4,328 | |
| GPT-5.4 Mini | 8.6 | 7.9 | 91.7% | 1 | 4.05s | 606 | 296 | 2,876 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 40.66s | 7,509 | 378 | 81,978 | |
| GPT-5.4 Mini | 8.4 | 7.4 | 88.9% | 1 | 57.87s | 7,305 | 467 | 40,902 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 24.73s | 77,368 | 4,906 | 24,016 | |
| GPT-5.4 Mini | 6.9 | 5.9 | 66.7% | 1 | 59.64s | 74,058 | 4,347 | 40,924 |
| 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 | 6.5 | 10.0 | 50.0% | 0 | 3.80s | 2,397 | 120 | 1,149 | |
| GPT-5.4 Mini | 10.0 | 10.0 | 100.0% | 0 | 2.43s | 7,140 | 234 | 650 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 3.5 | 4.4 | 33.3% | 2 | 95.58s | 909 | 27 | 184,701 | |
| GPT-5.4 Mini | 3.6 | 7.2 | 22.2% | 1 | 71.05s | 628 | 60 | 49,875 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 4.34s | 549 | 117 | 1,319 | |
| GPT-5.4 Mini | 4.5 | 10.0 | 0.0% | 0 | 3.72s | 477 | 150 | 510 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 8.38s | 783 | 63 | 1,546 | |
| GPT-5.4 Mini | 9.8 | 10.0 | 100.0% | 0 | 2.13s | 660 | 96 | 1,185 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 8.2 | 7.7 | 77.8% | 1 | 9.39s | 828 | 273 | 14,502 | |
| GPT-5.4 Mini | 7.8 | 10.0 | 66.7% | 0 | 4.37s | 642 | 278 | 2,443 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 13.83s | 8,259 | 313 | 284 | |
| GPT-5.4 Mini | 4.7 | 1.6 | 66.7% | 1 | 9.62s | 5,453 | 251 | 2,594 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 3.0 | 10.0 | 0.0% | 0 | 46.86s | 261 | 13 | 27,759 | |
| GPT-5.4 Mini | 3.0 | 10.0 | 0.0% | 0 | 30.10s | 195 | 32 | 10,174 |
Quick Compare
Switch Comparison Pair
Claude Fable 5.1highvsGPT-5.4 MinimediumGPT-5.4 MinimediumvsGLM 5.3 FlashXmaxGPT-5.4 MinimediumvsQwen3.7 MaxnoneClaude Opus 4.7mediumvsDeepSeek V4.1 FlashlowDeepSeek V4.1 FlashlowvsGPT-5.6 LunahighDeepSeek V4.1 FlashlowvsNemotron 3 UltramediumFree AvailableGPT-5.4 MinimediumvsQwen3.8 2.4T A95BhighDeepSeek V4.1 FlashlowvsGPT-5.4 NanomediumDeepSeek V4.1 FlashlowvsGemini 3.8 FlashmediumGPT-5.4 MinimediumvsGLM 5.3highDeepSeek V4.1 FlashlowvsQwen3.5-27BmediumDeepSeek V4.1 FlashlowvsGLM 5.3 FlashXmax