- Rank
- #139
- Total Output Tokens
- 16,454
- Response Time (avg)
- 2.65s
- Total Cost
- $0.300
Gemini 3.5 Flash (minimal) vs Gemma 4 26B A4B (medium)
Gemma 4 26B A4B (medium) leads on average score with 6.8 vs 6.7. Gemma 4 26B A4B (medium) has the lower benchmark cost at $0.111 vs $0.300. Gemini 3.5 Flash (minimal) is faster at 2.65s vs 104.93s, with pass rates of 60.6% vs 69.7%.
- Rank
- #135
- Total Output Tokens
- 253,646
- Response Time (avg)
- 104.93s
- Total Cost
- $0.111
Recommended model
Gemini 3.5 Flash (minimal)
Its score stays close to the best score here (6.7 vs 6.8), while responding about 39.7x faster than Gemma 4 26B A4B (medium).
Detailed comparison
| Metric | Gemini 3.5 Flash Gemini 3.5 Flash minimal | Gemma 4 26B A4B Gemma 4 26B A4B medium Free Available |
|---|---|---|
| Score | 6.7 | 6.8 |
| Rank | #139 | #135 |
| Reliability | 10.0 | 10.0 |
| Consistency | 9.6 | 9.6 |
| Attempts | 66/66 | 66/66 |
| Tests Correct | ||
| Attempt pass rate | 60.6% | 69.7% |
| Flaky tests | 1 | 1 |
| Total Runs | 66 | 66 |
| Cost per result | 2.302 | 0.623 |
| Total Cost | $0.300 | $0.111 |
| Input Price | $1.500 / 1M | $0.120 / 1M |
| Output Price | $9.000 / 1M | $0.400 / 1M |
| Total Input Tokens | 100,762 | 77,528 |
| Output Tokens | 16,454 | 26,048 |
| Reasoning Tokens | 0 | 227,598 |
| Response Time (avg) | 2.65s | 104.93s |
| Response Time (max) | 25.26s | 912.19s |
| Response Time (total) | 58.21s | 2203.52s |
| Parameters | ~500B total (~20B active) | 25.2B total (3.8B active) |
| Availability | Closed | Open source |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#139 Gemini 3.5 Flash
minimal- Cost
- $0.041
- Time
- 20.4s
- Tokens
- 4,608 tok
#135 Gemma 4 26B A4B
medium
Invalid SVG
- Cost
- $0.000
- Time
- 300.0s
- Tokens
- 0 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 3.5 Flash | 6.5 | 10.0 | 50.0% | 0 | 892ms | 492 | 405 | 0 | |
| Gemma 4 26B A4B | 10.0 | 10.0 | 100.0% | 0 | 6.20s | 816 | 1,142 | 3,045 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash | 5.6 | 9.9 | 33.3% | 0 | 2.75s | 8,122 | 3,456 | 0 | |
| Gemma 4 26B A4B | 2.9 | 10.0 | 0.0% | 0 | 272.54s | 5,062 | 14,838 | 44,567 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash | 3.0 | 10.0 | 0.0% | 0 | 14.41s | 76,686 | 11,581 | 0 | |
| Gemma 4 26B A4B | 6.3 | 10.0 | 50.0% | 0 | 492.87s | 54,390 | 5,451 | 132,113 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 1.66s | 7,548 | 279 | 0 | |
| Gemma 4 26B A4B | 10.0 | 10.0 | 100.0% | 0 | 16.51s | 8,334 | 1,567 | 2,827 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash | 7.7 | 10.0 | 66.7% | 0 | 879ms | 642 | 12 | 0 | |
| Gemma 4 26B A4B | 5.3 | 7.2 | 44.4% | 1 | 35.14s | 494 | 481 | 15,212 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 922ms | 486 | 117 | 0 | |
| Gemma 4 26B A4B | 10.0 | 10.0 | 100.0% | 0 | 29.76s | 567 | 25 | 5,075 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash | 6.4 | 5.8 | 66.7% | 1 | 893ms | 615 | 76 | 0 | |
| Gemma 4 26B A4B | 10.0 | 10.0 | 100.0% | 0 | 17.54s | 777 | 887 | 4,470 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 1.45s | 558 | 282 | 0 | |
| Gemma 4 26B A4B | 10.0 | 10.0 | 100.0% | 0 | 5.79s | 801 | 410 | 2,128 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.79s | 5,457 | 234 | 0 | |
| Gemma 4 26B A4B | 10.0 | 10.0 | 100.0% | 0 | 9.01s | 6,096 | 450 | 1,256 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash | 3.0 | 10.0 | 0.0% | 0 | 1.76s | 156 | 12 | 0 | |
| Gemma 4 26B A4B | 3.0 | 10.0 | 0.0% | 0 | 180.87s | 191 | 797 | 16,905 |
Quick Compare
Switch Comparison Pair
Gemini 3.5 FlashminimalvsLongCat 2.0lowGemma 4 26B A4BmediumFree AvailablevsGLM 5.2noneGemma 4 26B A4BmediumFree AvailablevsKAT-Coder-Pro V2.5noneGemini 3.5 FlashminimalvsLongCat 2.0highDeepSeek V4 PrononevsGemma 4 26B A4BmediumFree AvailableGemini 3.5 FlashminimalvsKAT-Coder-Pro V2.5noneGemini 3.5 FlashminimalvsGLM 5.2noneGemma 4 26B A4BmediumFree AvailablevsLongCat 2.0lowGemma 4 26B A4BmediumFree AvailablevsSolar Pro 4lowGemini 3.5 FlashminimalvsQwen3.5-27BnoneGemini 3.5 FlashminimalvsMiMo-V2.5-PromediumGemma 4 26B A4BmediumFree AvailablevsLongCat 2.0high