#51 Step 3.7 Flash
low
Invalid SVG
- Cost
- $0.004
- Time
- 25.3s
- Tokens
- 3,072 tok
AI BENCHY Compare
StepFun: Step 3.7 Flash vs xAI: Grok 4.3
Summary
The average score is effectively tied at 7.7 vs 7.7. Step 3.7 Flash (low) has the lower benchmark cost at $0.341 vs $0.614. Step 3.7 Flash (low) is faster at 15.74s vs 47.51s, with pass rates of 68.3% vs 71.4%.
Recommended modelStep 3.7 Flash (low)It has the best score here (7.7), while costing about 1.8x less than Grok 4.3 (medium).
Last updated at: 2026-07-14
| Metric | Step 3.7 Flash Step 3.7 Flash low | Grok 4.3 Grok 4.3 medium |
|---|---|---|
| Score | 7.7 | 7.7 |
| Rank | #51 | #48 |
| Reliability | 10.0 | 10.0 |
| Consistency | 8.4 | 8.5 |
| Tests Correct | ||
| Attempt pass rate | 68.3% | 71.4% |
| Flaky tests | 4 | 4 |
| Total Runs | 63 | 63 |
| Cost per result | 2.840 | 4.724 |
| Total Cost | $0.341 | $0.614 |
| Input Price | $0.200 / 1M | $1.250 / 1M |
| Output Price | $1.150 / 1M | $2.500 / 1M |
| Total Input Tokens | 40,101 | 44,472 |
| Output Tokens | 289,325 | 1,981 |
| Reasoning Tokens | 0 | 221,382 |
| Response Time (avg) | 15.74s | 47.51s |
| Response Time (max) | 124.75s | 216.69s |
| Response Time (total) | 330.63s | 997.68s |
Generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#48 xAI: Grok 4.3
medium- Cost
- $0.009
- Time
- 19.0s
- Tokens
- 3,661 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
| 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 | |
| Grok 4.3 | 5.9 | 7.7 | 44.4% | 1 | 41.23s | 8,340 | 1,028 | 31,226 |
Quick Compare
Switch Comparison Pair
GPT-5.6 LunahighvsStep 3.7 FlashlowClaude Opus 4.6mediumvsStep 3.7 FlashlowGPT-5.6 TerralowvsGrok 4.3mediumClaude Opus 4.8lowvsGrok 4.3mediumGPT-5.6 LunahighvsGrok 4.3mediumKAT-Coder-Pro V2.5highvsStep 3.7 FlashlowQwen3.5-122B-A10BmediumvsStep 3.7 FlashlowKAT-Coder-Pro V2.5highvsGrok 4.3mediumKimi K2.6mediumFree AvailablevsStep 3.7 FlashlowGemini 3.1 Flash LitemediumvsStep 3.7 FlashlowQwen3.5 Plus 2026-04-20mediumvsStep 3.7 FlashlowGemini 3.1 Flash Lite PreviewmediumvsStep 3.7 Flashlow