- Rank
- #10
- Total Output Tokens
- 239,608
- Response Time (avg)
- 19.86s
- Total Cost
- $0.763
Gemini 3 Flash Preview (medium) vs Step 3.7 Flash (low)
Gemini 3 Flash Preview (medium) leads on average score with 9.5 vs 7.1. Step 3.7 Flash (low) has the lower benchmark cost at $0.390 vs $0.763. Step 3.7 Flash (low) is faster at 17.87s vs 19.86s, with pass rates of 93.9% vs 63.6%.
Compared models
- Rank
- #137
- Total Output Tokens
- 320,393
- Response Time (avg)
- 17.87s
- Total Cost
- $0.390
Recommended model
Gemini 3 Flash Preview (medium)
It has the strongest score in this comparison (9.5) and the best overall balance of cost and response time across all 2 models.
Detailed comparison
| Metric | Gemini 3 Flash Preview Gemini 3 Flash Preview medium | Step 3.7 Flash Step 3.7 Flash low |
|---|---|---|
| Score | 9.5 | 7.1 |
| Rank | #10 | #137 |
| Reliability | 10.0 | 10.0 |
| Consistency | 9.7 | 8.1 |
| Attempts | 66/66 | 66/66 |
| Tests Correct | ||
| Attempt pass rate | 93.9% | 63.6% |
| Flaky tests | 1 | 5 |
| Total Runs | 66 | 66 |
| Cost per result | 3.814 | 3.539 |
| Total Cost | $0.763 | $0.390 |
| Input Price | $0.500 / 1M | $0.200 / 1M |
| Output Price | $3.000 / 1M | $1.150 / 1M |
| Total Input Tokens | 87,870 | 103,842 |
| Output Tokens | 5,486 | 320,393 |
| Reasoning Tokens | 234,122 | 0 |
| Response Time (avg) | 19.86s | 17.87s |
| Response Time (max) | 117.26s | 124.75s |
| Response Time (total) | 436.88s | 393.04s |
| Parameters | ~500B total (~20B active) | 198B total (11B active) |
| Availability | Closed | Open source |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#10 Gemini 3 Flash Preview
medium- Cost
- $0.010
- Time
- 18.4s
- Tokens
- 3,351 tok
#137 Step 3.7 Flash
low
Invalid SVG
- Cost
- $0.004
- Time
- 25.3s
- Tokens
- 3,072 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 |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 3.88s | 494 | 330 | 3,216 | |
| Step 3.7 Flash | 8.7 | 7.9 | 91.7% | 1 | 4.02s | 756 | 10,896 | 0 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 8.6 | 7.6 | 88.9% | 1 | 84.40s | 8,122 | 462 | 161,084 | |
| Step 3.7 Flash | 8.2 | 7.2 | 88.9% | 1 | 9.46s | 7,437 | 18,685 | 0 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 26.75s | 63,717 | 3,831 | 23,496 | |
| Step 3.7 Flash | 7.3 | 5.8 | 83.3% | 1 | 66.18s | 77,415 | 93,682 | 0 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 5.43s | 7,548 | 279 | 4,893 | |
| Step 3.7 Flash | 7.3 | 5.8 | 83.3% | 1 | 2.29s | 7,398 | 2,667 | 0 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 7.7 | 10.0 | 66.7% | 0 | 20.09s | 642 | 12 | 28,642 | |
| Step 3.7 Flash | 2.9 | 7.2 | 11.1% | 1 | 22.65s | 837 | 48,299 | 0 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 5.19s | 486 | 72 | 1,905 | |
| Step 3.7 Flash | 3.4 | 9.3 | 0.0% | 0 | 7.00s | 525 | 4,604 | 0 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 4.04s | 615 | 72 | 2,709 | |
| Step 3.7 Flash | 9.8 | 10.0 | 100.0% | 0 | 1.58s | 735 | 1,857 | 0 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 4.05s | 558 | 183 | 4,365 | |
| Step 3.7 Flash | 5.5 | 9.9 | 33.3% | 0 | 1.84s | 756 | 3,564 | 0 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 12.60s | 5,532 | 234 | 1,487 | |
| Step 3.7 Flash | 10.0 | 10.0 | 100.0% | 0 | 3.25s | 7,746 | 1,360 | 0 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 5.50s | 156 | 11 | 2,325 | |
| Step 3.7 Flash | 3.0 | 10.0 | 0.0% | 0 | 124.75s | 237 | 134,779 | 0 |
Quick Compare
Switch Comparison Pair
Gemini 3 Flash PreviewmediumvsGPT-6 AstralowQwen3.5-122B-A10BmediumvsStep 3.7 FlashlowStep 3.7 FlashlowvsSolar Pro 4highMuse Glimmer 30BmediumvsStep 3.7 FlashlowMercury 2.5highvsStep 3.7 FlashlowQwen3.5 Plus 2026-04-20mediumvsStep 3.7 FlashlowGemini 3 Flash PreviewmediumvsGPT-5.6 SollowMuse Glimmer 30BhighvsStep 3.7 FlashlowStep 3.7 FlashlowvsGrok 4.3mediumGPT-5.6 SolnonevsStep 3.7 FlashlowKAT-Coder-Pro V2.5highvsStep 3.7 FlashlowGemini 3 Flash PreviewmediumvsGPT-5.6 Solhigh