- Rank
- #147
- Total Output Tokens
- 339,108
- Response Time (avg)
- 20.72s
- Total Cost
- $0.449
Step 3.7 Flash (low) vs GLM 5.3 FlashX (medium)
Step 3.7 Flash (low) leads on average score with 7.2 vs 7.1. GLM 5.3 FlashX (medium) has the lower benchmark cost at $0.114 vs $0.449. GLM 5.3 FlashX (medium) is faster at 7.37s vs 20.72s, with pass rates of 63.8% vs 69.6%.
Compared models
- Rank
- #150
- Total Output Tokens
- 30,048
- Response Time (avg)
- 7.37s
- Total Cost
- $0.114
Recommended model
GLM 5.3 FlashX (medium)
Its score stays close to the best score here (7.1 vs 7.2), while costing about 4.0x less than Step 3.7 Flash (low).
Detailed comparison
| Metric | Step 3.7 Flash Step 3.7 Flash low | GLM 5.3 FlashX GLM 5.3 FlashX medium |
|---|---|---|
| Score | 7.2 | 7.1 |
| Rank | #147 | #150 |
| Reliability | 10.0 | 10.0 |
| Consistency | 7.9 | 7.1 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 63.8% | 69.6% |
| Flaky tests | 6 | 8 |
| Total Runs | 69 | 69 |
| Cost per result | 4.078 | 0.946 |
| Total Cost | $0.449 | $0.114 |
| Input Price | $0.200 / 1M | $0.370 / 1M |
| Output Price | $1.150 / 1M | $1.250 / 1M |
| Total Input Tokens | 292,685 | 205,100 |
| Output Tokens | 339,108 | 8,639 |
| Reasoning Tokens | 0 | 21,409 |
| Response Time (avg) | 20.72s | 7.37s |
| Response Time (max) | 124.75s | 74.39s |
| Response Time (total) | 476.67s | 169.54s |
| Parameters | 198B total (11B active) | 320B total (18B active) |
| Availability | Open source | Closed |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#147 Step 3.7 Flash
low
Invalid SVG
- Cost
- $0.004
- Time
- 25.3s
- Tokens
- 3,072 tok
#150 GLM 5.3 FlashX
medium- Cost
- $0.002
- Time
- 8.1s
- Tokens
- 1,480 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 |
|---|---|---|---|---|---|---|---|---|---|
| Step 3.7 Flash | 7.4 | 3.8 | 66.7% | 1 | 83.63s | 188,843 | 18,715 | 0 | |
| GLM 5.3 FlashX | 10.0 | 10.0 | 100.0% | 0 | 74.39s | 120,771 | 922 | 9,693 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Step 3.7 Flash | 8.7 | 7.9 | 91.7% | 1 | 4.02s | 756 | 10,896 | 0 | |
| GLM 5.3 FlashX | 7.3 | 5.8 | 83.3% | 2 | 1.71s | 639 | 343 | 368 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Step 3.7 Flash | 8.2 | 7.2 | 88.9% | 1 | 9.46s | 7,437 | 18,685 | 0 | |
| GLM 5.3 FlashX | 6.0 | 4.6 | 66.7% | 2 | 6.37s | 7,317 | 384 | 5,562 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Step 3.7 Flash | 7.3 | 5.8 | 83.3% | 1 | 66.18s | 77,415 | 93,682 | 0 | |
| GLM 5.3 FlashX | 2.8 | 1.6 | 33.3% | 2 | 15.97s | 59,549 | 5,920 | 2,786 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Step 3.7 Flash | 7.3 | 5.8 | 83.3% | 1 | 2.29s | 7,398 | 2,667 | 0 | |
| GLM 5.3 FlashX | 10.0 | 10.0 | 100.0% | 0 | 1.74s | 7,149 | 210 | 134 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Step 3.7 Flash | 2.9 | 7.2 | 11.1% | 1 | 22.65s | 837 | 48,299 | 0 | |
| GLM 5.3 FlashX | 3.6 | 7.2 | 22.2% | 1 | 3.52s | 759 | 38 | 2,005 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Step 3.7 Flash | 3.4 | 9.3 | 0.0% | 0 | 7.00s | 525 | 4,604 | 0 | |
| GLM 5.3 FlashX | 3.4 | 2.2 | 33.3% | 1 | 1.79s | 498 | 135 | 0 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Step 3.7 Flash | 9.8 | 10.0 | 100.0% | 0 | 1.58s | 735 | 1,857 | 0 | |
| GLM 5.3 FlashX | 10.0 | 10.0 | 100.0% | 0 | 1.51s | 678 | 72 | 70 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Step 3.7 Flash | 5.5 | 9.9 | 33.3% | 0 | 1.84s | 756 | 3,564 | 0 | |
| GLM 5.3 FlashX | 10.0 | 10.0 | 100.0% | 0 | 1.84s | 672 | 306 | 371 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Step 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 3.25s | 7,746 | 1,360 | 0 | |
| GLM 5.3 FlashX | 10.0 | 10.0 | 100.0% | 0 | 10.30s | 6,861 | 231 | 20 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Step 3.7 Flash | 3.0 | 10.0 | 0.0% | 0 | 124.75s | 237 | 134,779 | 0 | |
| GLM 5.3 FlashX | 3.0 | 10.0 | 0.0% | 0 | 2.60s | 207 | 78 | 400 |
Quick Compare
Switch Comparison Pair
Step 3.7 FlashlowvsGLM 5mediumMiMo-V2.6-FlashlowvsGLM 5.3 FlashXmediumLongCat 2.0mediumvsStep 3.7 FlashlowQwen3.6 27BmediumvsStep 3.7 FlashlowQwen3.7 FlashhighvsStep 3.7 FlashlowClaude Opus 5nonevsStep 3.7 FlashlowQwen3.8 27BmediumFree AvailablevsStep 3.7 FlashlowGPT-5.2 ChatnonevsGLM 5.3 FlashXmediumQwen3.5 Plus 2026-02-15mediumvsStep 3.7 FlashlowQwen3.5-27BnonevsStep 3.7 FlashlowClaude Opus 5nonevsGLM 5.3 FlashXmediumEmber-1lowvsGLM 5.3 FlashXmedium