- Rank
- #193
- Total Output Tokens
- 776,174
- Response Time (avg)
- 59.92s
- Total Cost
- $0.812
Qwen3.6 35B A3B (medium) vs Step 3.7 Flash (high)
Step 3.7 Flash (high) leads on average score with 6.6 vs 6.5. Qwen3.6 35B A3B (medium) has the lower benchmark cost at $0.812 vs $1.350. Qwen3.6 35B A3B (medium) is faster at 59.92s vs 72.72s, with pass rates of 58.0% vs 58.0%.
Compared models
- Rank
- #190
- Total Output Tokens
- 1,100,052
- Response Time (avg)
- 72.72s
- Total Cost
- $1.350
Recommended model
Qwen3.6 35B A3B (medium)
Its score stays close to the best score here (6.5 vs 6.6), while costing about 1.7x less than Step 3.7 Flash (high).
Detailed comparison
| Metric | Qwen3.6 35B A3B Qwen3.6 35B A3B medium | Step 3.7 Flash Step 3.7 Flash high |
|---|---|---|
| Score | 6.5 | 6.6 |
| Rank | #193 | #190 |
| Reliability | 10.0 | 10.0 |
| Consistency | 9.0 | 8.5 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 58.0% | 58.0% |
| Flaky tests | 3 | 4 |
| Total Runs | 69 | 69 |
| Cost per result | 6.732 | 12.267 |
| Total Cost | $0.812 | $1.350 |
| Input Price | $0.150 / 1M | $0.200 / 1M |
| Output Price | $1.000 / 1M | $1.150 / 1M |
| Total Input Tokens | 282,192 | 421,200 |
| Output Tokens | 75,306 | 1,100,052 |
| Reasoning Tokens | 700,868 | 0 |
| Response Time (avg) | 59.92s | 72.72s |
| Response Time (max) | 817.57s | 364.99s |
| Response Time (total) | 1258.32s | 1672.53s |
| Parameters | 35B total (3B active) | 198B total (11B active) |
| Availability | Open source | Open source |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#193 Qwen3.6 35B A3B
medium
Reached the allocated time limit (300 seconds) without receiving showcase output.
- Cost
- $0.000
- Time
- 300.0s
- Tokens
- 0 tok
#190 Step 3.7 Flash
high- Cost
- $0.007
- Time
- 63.6s
- Tokens
- 6,030 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 |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.6 35B A3B | 6.1 | 3.1 | 66.7% | 1 | 88.48s | 197,044 | 13,570 | 19,312 | |
| Step 3.7 Flash | 5.4 | 9.6 | 0.0% | 0 | 130.38s | 322,500 | 49,152 | 0 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.6 35B A3B | 10.0 | 10.0 | 100.0% | 0 | 6.02s | 672 | 1,154 | 12,385 | |
| Step 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 13.40s | 696 | 42,656 | 0 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.6 35B A3B | 7.7 | 10.0 | 66.7% | 0 | 50.55s | 5,051 | 7,929 | 37,223 | |
| Step 3.7 Flash | 4.0 | 6.0 | 22.2% | 1 | 206.21s | 6,057 | 327,340 | 0 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.6 35B A3B | 3.0 | 10.0 | 0.0% | 0 | 817.57s | 68,754 | 42,187 | 548,547 | |
| Step 3.7 Flash | 8.7 | 6.9 | 83.3% | 1 | 41.23s | 73,938 | 49,842 | 0 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.6 35B A3B | 10.0 | 10.0 | 100.0% | 0 | 12.99s | 7,776 | 2,591 | 9,968 | |
| Step 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 14.72s | 7,368 | 23,113 | 0 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.6 35B A3B | 2.9 | 4.4 | 22.2% | 2 | 25.39s | 780 | 6,110 | 41,906 | |
| Step 3.7 Flash | 3.6 | 7.2 | 22.2% | 1 | 189.35s | 792 | 429,007 | 0 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.6 35B A3B | 4.4 | 9.9 | 0.0% | 0 | 8.66s | 516 | 129 | 4,569 | |
| Step 3.7 Flash | 5.5 | 10.0 | 0.0% | 0 | 4.17s | 510 | 2,862 | 0 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.6 35B A3B | 10.0 | 10.0 | 100.0% | 0 | 7.50s | 699 | 219 | 7,404 | |
| Step 3.7 Flash | 9.8 | 10.0 | 100.0% | 0 | 1.52s | 705 | 2,010 | 0 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.6 35B A3B | 8.0 | 10.0 | 66.7% | 0 | 5.95s | 696 | 655 | 9,228 | |
| Step 3.7 Flash | 5.3 | 7.2 | 44.4% | 1 | 10.22s | 711 | 25,422 | 0 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.6 35B A3B | 3.0 | 10.0 | 0.0% | 0 | 0ms | 0 | 0 | 0 | |
| Step 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.79s | 7,701 | 1,172 | 0 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.6 35B A3B | 3.0 | 10.0 | 0.0% | 0 | 32.90s | 204 | 762 | 10,326 | |
| Step 3.7 Flash | 3.0 | 10.0 | 0.0% | 0 | 149.34s | 222 | 147,476 | 0 |
Quick Compare
Switch Comparison Pair
Mercury 2mediumvsStep 3.7 FlashhighMercury 2.5 PreviewhighvsQwen3.6 35B A3BmediumKAT-Coder-Pro V2.5lowvsStep 3.7 FlashhighMercury 2.5highvsQwen3.6 35B A3BmediumQwen3.6 35B A3BmediumvsGLM 5.3lowLongCat 2.0lowvsStep 3.7 FlashhighQwen3.7 FlashmediumvsStep 3.7 FlashhighQwen3.6 35B A3BmediumvsGLM 5.1noneKAT-Coder-Pro V2.5lowvsQwen3.6 35B A3BmediumKAT-Coder-Pro V2.5highvsQwen3.6 35B A3BmediumClaude Sonnet 5.5mediumvsStep 3.7 FlashhighStep 3.7 FlashhighvsGLM 5.2none