- Rank
- #27
- Total Output Tokens
- 105,662
- Response Time (avg)
- 25.31s
- Total Cost
- $4.524
Claude Opus 5 (high) vs Gemini 3 Flash Preview (medium)
Gemini 3 Flash Preview (medium) leads on average score with 9.6 vs 9.4. Gemini 3 Flash Preview (medium) has the lower benchmark cost at $0.876 vs $4.524. Gemini 3 Flash Preview (medium) is faster at 21.57s vs 25.31s, with pass rates of 82.6% vs 94.2%.
Compared models
- Rank
- #15
- Total Output Tokens
- 252,536
- Response Time (avg)
- 21.57s
- Total Cost
- $0.876
Recommended model
Gemini 3 Flash Preview (medium)
It has the best score here (9.6), while costing about 5.2x less than Claude Opus 5 (high).
Detailed comparison
| Metric | Claude Opus 5 Claude Opus 5 high | Gemini 3 Flash Preview Gemini 3 Flash Preview medium |
|---|---|---|
| Score | 9.4 | 9.6 |
| Rank | #27 | #15 |
| Reliability | 10.0 | 10.0 |
| Consistency | 10.0 | 9.7 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 82.6% | 94.2% |
| Flaky tests | 0 | 1 |
| Total Runs | 69 | 69 |
| Cost per result | 23.809 | 4.169 |
| Total Cost | $4.524 | $0.876 |
| Input Price | $5.000 / 1M | $0.500 / 1M |
| Output Price | $25.000 / 1M | $3.000 / 1M |
| Cache Read Price | $0.500 / 1M | $0.050 / 1M |
| Cache Write Price | $6.250 / 1M | $0.084 / 1M |
| Total Input Tokens | 376,421 | 235,726 |
| Output Tokens | 67,688 | 6,669 |
| Reasoning Tokens | 37,974 | 245,867 |
| Response Time (avg) | 25.31s | 21.57s |
| Response Time (max) | 159.01s | 117.26s |
| Response Time (total) | 582.11s | 496.12s |
| Parameters | ~5T total (~500B active) | ~500B total (~20B active) |
| Availability | Closed | Closed |
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#27 Claude Opus 5
high- Cost
- $0.265
- Time
- 144.5s
- Tokens
- 10,741 tok
#15 Gemini 3 Flash Preview
medium- Cost
- $0.010
- Time
- 18.4s
- Tokens
- 3,351 tok
Category Breakdown
| Agentic | 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 | 86.99s | 240,465 | 3,064 | 7,015 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 59.24s | 147,856 | 1,183 | 11,745 |
| 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 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 3.88s | 494 | 330 | 3,216 |
| 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 Flash Preview | 8.6 | 7.6 | 88.9% | 1 | 84.40s | 8,122 | 462 | 161,084 |
| 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 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 26.75s | 63,717 | 3,831 | 23,496 |
| 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 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 5.43s | 7,548 | 279 | 4,893 |
| 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 Flash Preview | 7.7 | 10.0 | 66.7% | 0 | 20.09s | 642 | 12 | 28,642 |
| 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 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 5.19s | 486 | 72 | 1,905 |
| 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 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 4.04s | 615 | 72 | 2,709 |
| 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 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 4.05s | 558 | 183 | 4,365 |
| 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 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 12.60s | 5,532 | 234 | 1,487 |
| 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 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 5.50s | 156 | 11 | 2,325 |
Quick Compare
Switch Comparison Pair
Gemini 3 Flash PreviewmediumvsGPT-6.1 SollowGemini 3 Flash PreviewmediumvsGPT-6 AstralowClaude Opus 5highvsGemini 3.7 FlashlowGemini 3 Flash PreviewmediumvsGPT-5.6 SollowGemini 3 Flash PreviewmediumvsGPT-6.1 SolhighGemini 3 Flash PreviewmediumvsGPT-5.6 SolhighClaude Opus 5highvsSeed 2.1 TurbolowClaude Opus 5highvsGPT-5.5lowGemini 3 Flash PreviewmediumvsGPT-5.5lowClaude Opus 5highvsGPT-6 AstramediumClaude Opus 5highvsGPT-5.6 SolmediumClaude Opus 5highvsGPT-6 Solmedium