- Rank
- #52
- Total Output Tokens
- 452,940
- Response Time (avg)
- 32.78s
- Total Cost
- $0.287
DeepSeek V4.1 Flash (high) vs Qwen3.6 Max Preview (medium)
Qwen3.6 Max Preview (medium) leads on average score with 8.6 vs 8.5. DeepSeek V4.1 Flash (high) has the lower benchmark cost at $0.287 vs $1.132. DeepSeek V4.1 Flash (high) is faster at 32.78s vs 66.52s, with pass rates of 74.2% vs 83.3%.
Compared models
- Rank
- #48
- Total Output Tokens
- 170,373
- Response Time (avg)
- 66.52s
- Total Cost
- $1.132
Recommended model
DeepSeek V4.1 Flash (high)
Its score stays close to the best score here (8.5 vs 8.6), while costing about 3.9x less than Qwen3.6 Max Preview (medium).
Detailed comparison
| Metric | DeepSeek V4.1 Flash DeepSeek V4.1 Flash high | Qwen3.6 Max Preview Qwen3.6 Max Preview medium |
|---|---|---|
| Score | 8.5 | 8.6 |
| Rank | #52 | #48 |
| Reliability | 9.6 | 10.0 |
| Consistency | 8.9 | 9.3 |
| Attempts | 66/66 | 66/66 |
| Tests Correct | ||
| Attempt pass rate | 74.2% | 83.3% |
| Flaky tests | 3 | 2 |
| Total Runs | 66 | 66 |
| Cost per result | 1.912 | 7.653 |
| Total Cost | $0.287 | $1.132 |
| Input Price | $0.150 / 1M | $1.028 / 1M |
| Output Price | $0.600 / 1M | $6.162 / 1M |
| Total Input Tokens | 100,111 | 79,249 |
| Output Tokens | 6,642 | 5,097 |
| Reasoning Tokens | 446,298 | 165,276 |
| Response Time (avg) | 32.78s | 66.52s |
| Response Time (max) | 205.53s | 238.07s |
| Response Time (total) | 721.15s | 1463.50s |
| Parameters | 748B total (16B active) | ~1T total (~40B active) |
| Availability | Open source | Closed |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#52 DeepSeek V4.1 Flash
high- Cost
- $0.035
- Time
- 111.0s
- Tokens
- 29,201 tok
#48 Qwen3.6 Max Preview
medium- Cost
- $0.024
- Time
- 76.5s
- Tokens
- 3,861 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
| 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 | 3.42s | 852 | 170 | 5,348 | |
| Qwen3.6 Max Preview | 10.0 | 10.0 | 100.0% | 0 | 22.13s | 672 | 228 | 10,075 |
| 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 | 49.19s | 7,509 | 376 | 108,285 | |
| Qwen3.6 Max Preview | 8.8 | 7.8 | 88.9% | 1 | 146.48s | 7,895 | 427 | 52,957 |
| 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 | 27.63s | 77,764 | 5,152 | 31,635 | |
| Qwen3.6 Max Preview | 7.3 | 5.8 | 83.3% | 1 | 177.48s | 51,812 | 3,215 | 35,050 |
| 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 | 4.19s | 2,397 | 120 | 1,584 | |
| Qwen3.6 Max Preview | 10.0 | 10.0 | 100.0% | 0 | 41.15s | 7,782 | 270 | 10,106 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 5.3 | 7.2 | 44.4% | 1 | 127.30s | 909 | 28 | 249,623 | |
| Qwen3.6 Max Preview | 5.3 | 10.0 | 33.3% | 0 | 88.53s | 780 | 59 | 30,805 |
| 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 | 4.16s | 549 | 120 | 1,130 | |
| Qwen3.6 Max Preview | 10.0 | 10.0 | 100.0% | 0 | 32.24s | 516 | 129 | 3,510 |
| 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 | 7.06s | 783 | 63 | 1,972 | |
| Qwen3.6 Max Preview | 10.0 | 10.0 | 100.0% | 0 | 24.31s | 699 | 103 | 5,848 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 6.4 | 4.9 | 66.7% | 2 | 14.27s | 828 | 339 | 23,969 | |
| Qwen3.6 Max Preview | 10.0 | 10.0 | 100.0% | 0 | 24.32s | 696 | 329 | 7,693 |
| 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 | 15.28s | 8,259 | 258 | 506 | |
| Qwen3.6 Max Preview | 10.0 | 10.0 | 100.0% | 0 | 18.32s | 8,193 | 309 | 1,571 |
| 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 | 38.05s | 261 | 16 | 22,246 | |
| Qwen3.6 Max Preview | 3.0 | 10.0 | 0.0% | 0 | 60.56s | 204 | 28 | 7,661 |
Quick Compare
Switch Comparison Pair
DeepSeek V4.1 FlashhighvsGrok 4.5mediumDeepSeek V4.1 FlashhighvsMuse Spark 1.2lowDeepSeek V4.1 FlashhighvsGrok 4.6mediumDeepSeek V4.1 FlashhighvsGPT-5.4mediumDeepSeek V4.1 FlashhighvsGrok 4.5lowDeepSeek V4.1 FlashhighvsGPT-5.2mediumDeepSeek V4.1 FlashhighvsQwen3.8 MaxlowMuse Spark 1.2highvsQwen3.6 Max PreviewmediumSeed 2.1 TurbomediumvsDeepSeek V4.1 FlashhighDeepSeek V4.1 FlashlowvsQwen3.6 Max PreviewmediumMuse Spark 1.2lowvsQwen3.6 Max PreviewmediumQwen3.6 Max PreviewmediumvsGLM 5.3 Flashmax