- Rank
- #11
- Total Output Tokens
- 239,608
- Response Time (avg)
- 19.86s
- Total Cost
- $0.763
Gemini 3 Flash Preview (medium) vs GPT-6 Sol (medium)
Gemini 3 Flash Preview (medium) leads on average score with 9.5 vs 9.4. GPT-6 Sol (medium) has the lower benchmark cost at $0.448 vs $0.763. GPT-6 Sol (medium) is faster at 10.33s vs 19.86s, with pass rates of 93.9% vs 93.9%.
Compared models
- Rank
- #14
- Total Output Tokens
- 29,115
- Response Time (avg)
- 10.33s
- Total Cost
- $0.448
Recommended model
GPT-6 Sol (medium)
Its score stays close to the best score here (9.4 vs 9.5), while costing about 1.7x less than Gemini 3 Flash Preview (medium).
Detailed comparison
| Metric | Gemini 3 Flash Preview Gemini 3 Flash Preview medium | GPT-6 Sol GPT-6 Sol medium |
|---|---|---|
| Score | 9.5 | 9.4 |
| Rank | #11 | #14 |
| Reliability | 10.0 | 10.0 |
| Consistency | 9.7 | 9.6 |
| Attempts | 66/66 | 66/66 |
| Tests Correct | ||
| Attempt pass rate | 93.9% | 93.9% |
| Flaky tests | 1 | 1 |
| Total Runs | 66 | 66 |
| Cost per result | 3.814 | 2.240 |
| Total Cost | $0.763 | $0.448 |
| Input Price | $0.500 / 1M | $2.000 / 1M |
| Output Price | $3.000 / 1M | $10.000 / 1M |
| Total Input Tokens | 87,870 | 78,376 |
| Output Tokens | 5,486 | 4,309 |
| Reasoning Tokens | 234,122 | 24,806 |
| Response Time (avg) | 19.86s | 10.33s |
| Response Time (max) | 117.26s | 82.74s |
| Response Time (total) | 436.88s | 227.17s |
| Parameters | ~500B total (~20B active) | ~2T total (~150B active) |
| Availability | Closed | Closed |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#11 Gemini 3 Flash Preview
medium- Cost
- $0.010
- Time
- 18.4s
- Tokens
- 3,351 tok
#14 GPT-6 Sol
medium- Cost
- $0.035
- Time
- 36.9s
- Tokens
- 3,493 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 | |
| GPT-6 Sol | 10.0 | 10.0 | 100.0% | 0 | 2.70s | 606 | 142 | 564 |
| 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 | |
| GPT-6 Sol | 8.2 | 7.2 | 88.9% | 1 | 11.78s | 7,302 | 392 | 2,532 |
| 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 | |
| GPT-6 Sol | 10.0 | 10.0 | 100.0% | 0 | 10.78s | 55,168 | 2,825 | 1,234 |
| 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 | |
| GPT-6 Sol | 10.0 | 10.0 | 100.0% | 0 | 7.34s | 7,140 | 234 | 162 |
| 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 | |
| GPT-6 Sol | 7.7 | 10.0 | 66.7% | 0 | 36.36s | 732 | 67 | 18,352 |
| 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 | |
| GPT-6 Sol | 10.0 | 10.0 | 100.0% | 0 | 13.97s | 477 | 90 | 136 |
| 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 | |
| GPT-6 Sol | 10.0 | 10.0 | 100.0% | 0 | 2.00s | 660 | 93 | 304 |
| 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 | |
| GPT-6 Sol | 10.0 | 10.0 | 100.0% | 0 | 2.79s | 642 | 196 | 724 |
| 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 | |
| GPT-6 Sol | 10.0 | 10.0 | 100.0% | 0 | 4.77s | 5,454 | 240 | 53 |
| 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 | |
| GPT-6 Sol | 10.0 | 10.0 | 100.0% | 0 | 4.61s | 195 | 30 | 745 |
Quick Compare
Switch Comparison Pair
Gemini 3 Flash PreviewmediumvsGPT-6 AstralowGPT-6 SolmediumvsGrok 4.6highGemini 3.5 FlashhighvsGPT-6 SolmediumClaude Opus 5.5lowvsGPT-6 SolmediumGemini 3 Flash PreviewmediumvsGPT-5.6 SollowClaude Opus 5.5highvsGPT-6 SolmediumGemini 3 Flash PreviewmediumvsGPT-5.6 SolhighGemini 3 Flash PreviewmediumvsGPT-5.5lowGemini 3 Flash PreviewmediumvsGrok 4.6highGemini 3.7 FlashlowvsGPT-6 SolmediumClaude Opus 5highvsGPT-6 SolmediumClaude Opus 5.5lowvsGemini 3 Flash Previewmedium