- Rank
- #20
- Total Output Tokens
- 95,583
- Response Time (avg)
- 22.51s
- Total Cost
- $3.070
Claude Opus 5 (high) vs Gemini 3.1 Pro Preview (medium)
The average score is effectively tied at 9.2 vs 9.2. Gemini 3.1 Pro Preview (medium) has the lower benchmark cost at $1.352 vs $3.070. Gemini 3.1 Pro Preview (medium) is faster at 20.62s vs 22.51s, with pass rates of 81.8% vs 90.9%.
Compared models
- Rank
- #18
- Total Output Tokens
- 97,238
- Response Time (avg)
- 20.62s
- Total Cost
- $1.352
Recommended model
Gemini 3.1 Pro Preview (medium)
It has the best score here (9.2), while costing about 2.3x less than Claude Opus 5 (high).
Detailed comparison
| Metric | Claude Opus 5 Claude Opus 5 high | Gemini 3.1 Pro Preview Gemini 3.1 Pro Preview medium |
|---|---|---|
| Score | 9.2 | 9.2 |
| Rank | #20 | #18 |
| Reliability | 10.0 | 10.0 |
| Consistency | 10.0 | 10.0 |
| Attempts | 66/66 | 66/66 |
| Tests Correct | ||
| Attempt pass rate | 81.8% | 90.9% |
| Flaky tests | 0 | 0 |
| Total Runs | 66 | 66 |
| Cost per result | 17.052 | 6.758 |
| Total Cost | $3.070 | $1.352 |
| Input Price | $5.000 / 1M | $2.000 / 1M |
| Output Price | $25.000 / 1M | $12.000 / 1M |
| Total Input Tokens | 135,956 | 92,296 |
| Output Tokens | 64,624 | 5,232 |
| Reasoning Tokens | 30,959 | 92,006 |
| Response Time (avg) | 22.51s | 20.62s |
| Response Time (max) | 159.01s | 88.68s |
| Response Time (total) | 495.12s | 329.94s |
| Parameters | ~5T total (~500B active) | ~1.2T total (~20B active) |
| Availability | Closed | Closed |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#20 Claude Opus 5
high- Cost
- $0.265
- Time
- 144.5s
- Tokens
- 10,741 tok
#18 Gemini 3.1 Pro Preview
medium- Cost
- $0.115
- Time
- 87.2s
- Tokens
- 9,629 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 |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 5.91s | 834 | 2,063 | 617 | |
| Gemini 3.1 Pro Preview | 10.0 | 10.0 | 100.0% | 0 | 7.90s | 498 | 112 | 3,218 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 12.73s | 10,590 | 7,547 | 1,721 | |
| Gemini 3.1 Pro Preview | 7.9 | 9.9 | 66.7% | 0 | 40.17s | 8,124 | 435 | 41,247 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 31.11s | 98,549 | 10,546 | 2,198 | |
| Gemini 3.1 Pro Preview | 9.8 | 10.0 | 100.0% | 0 | 40.39s | 67,910 | 3,687 | 23,111 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 4.22s | 10,503 | 488 | 160 | |
| Gemini 3.1 Pro Preview | 10.0 | 10.0 | 100.0% | 0 | 7.72s | 7,265 | 279 | 3,904 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 3.0 | 10.0 | 0.0% | 0 | 104.24s | 972 | 40,623 | 24,923 | |
| Gemini 3.1 Pro Preview | 7.7 | 10.0 | 66.7% | 0 | 20.29s | 644 | 18 | 11,704 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 3.79s | 708 | 268 | 0 | |
| Gemini 3.1 Pro Preview | 10.0 | 10.0 | 100.0% | 0 | 11.77s | 490 | 108 | 1,179 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 4.78s | 909 | 119 | 361 | |
| Gemini 3.1 Pro Preview | 10.0 | 10.0 | 100.0% | 0 | 9.56s | 621 | 72 | 2,236 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 4.66s | 894 | 908 | 524 | |
| Gemini 3.1 Pro Preview | 10.0 | 10.0 | 100.0% | 0 | 6.90s | 570 | 235 | 3,128 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 10.0 | 10.0 | 100.0% | 0 | 8.44s | 11,739 | 354 | 0 | |
| Gemini 3.1 Pro Preview | 10.0 | 10.0 | 100.0% | 0 | 23.15s | 6,018 | 274 | 982 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 3.0 | 10.0 | 0.0% | 0 | 14.14s | 258 | 1,708 | 455 | |
| Gemini 3.1 Pro Preview | 10.0 | 10.0 | 100.0% | 0 | 6.27s | 156 | 12 | 1,297 |
Quick Compare
Switch Comparison Pair
Claude Opus 5highvsGemini 3.7 FlashlowGemini 3.1 Pro PreviewmediumvsGrok 4.6highGemini 3.1 Pro PreviewmediumvsGPT-5.5lowClaude Opus 5highvsGemini 3.8 FlashmediumClaude Opus 5highvsQwen3.8 Max (0902)lowGemini 3.1 Pro PreviewmediumvsGPT-5.6 SolhighClaude Opus 5highvsSeed 2.1 TurbolowClaude Opus 5highvsGPT-5.5lowGemini 3.1 Pro PreviewmediumvsQwen3.8 Max (0902)lowClaude Opus 5highvsGPT-6 AstramediumSeed 2.1 TurbolowvsGemini 3.1 Pro PreviewmediumClaude Opus 5highvsGPT-5.6 Solmedium