- Rank
- #162
- Total Output Tokens
- 24,523
- Response Time (avg)
- 7.71s
- Total Cost
- $2.328
Claude Opus 4.8 vs Gemini 3 Flash Preview (low)
The average score is effectively tied at 6.9 vs 6.9. Gemini 3 Flash Preview (low) has the lower benchmark cost at $0.254 vs $2.328. Claude Opus 4.8 is faster at 7.71s vs 8.51s, with pass rates of 60.9% vs 72.5%.
Compared models
- Rank
- #160
- Total Output Tokens
- 42,400
- Response Time (avg)
- 8.51s
- Total Cost
- $0.254
Recommended model
Gemini 3 Flash Preview (low)
It has the best score here (6.9), while costing about 9.2x less than Claude Opus 4.8.
Detailed comparison
| Metric | Claude Opus 4.8 Claude Opus 4.8 none | Gemini 3 Flash Preview Gemini 3 Flash Preview low |
|---|---|---|
| Score | 6.9 | 6.9 |
| Rank | #162 | #160 |
| Reliability | 10.0 | 10.0 |
| Consistency | 9.3 | 9.3 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 60.9% | 72.5% |
| Flaky tests | 2 | 2 |
| Total Runs | 69 | 69 |
| Cost per result | 17.906 | 1.582 |
| Total Cost | $2.328 | $0.254 |
| Input Price | $5.000 / 1M | $0.500 / 1M |
| Output Price | $25.000 / 1M | $3.000 / 1M |
| Total Input Tokens | 342,921 | 251,677 |
| Output Tokens | 24,523 | 11,196 |
| Reasoning Tokens | 0 | 31,204 |
| Response Time (avg) | 7.71s | 8.51s |
| Response Time (max) | 69.14s | 52.64s |
| Response Time (total) | 177.38s | 195.76s |
| Parameters | ~5T total (~500B active) | ~500B 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.
#162 Claude Opus 4.8
none- Cost
- $0.053
- Time
- 22.0s
- Tokens
- 2,253 tok
#160 Gemini 3 Flash Preview
low- Cost
- $0.007
- Time
- 12.1s
- Tokens
- 2,289 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
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 5.4 | 9.6 | 0.0% | 0 | 69.14s | 193,718 | 7,726 | 0 | |
| Gemini 3 Flash Preview | 5.0 | 10.0 | 0.0% | 0 | 52.64s | 127,990 | 1,624 | 0 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 6.5 | 10.0 | 50.0% | 0 | 3.40s | 834 | 1,472 | 0 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 3.48s | 500 | 281 | 3,082 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 5.5 | 10.0 | 33.3% | 0 | 3.29s | 10,590 | 1,332 | 0 | |
| Gemini 3 Flash Preview | 5.8 | 7.2 | 44.4% | 1 | 6.00s | 8,122 | 456 | 7,421 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 9.8 | 10.0 | 100.0% | 0 | 26.38s | 111,760 | 11,949 | 0 | |
| Gemini 3 Flash Preview | 3.0 | 10.0 | 0.0% | 0 | 10.20s | 99,775 | 7,822 | 0 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 7.3 | 5.8 | 83.3% | 1 | 1.77s | 10,503 | 308 | 0 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 9.40s | 7,261 | 279 | 3,656 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 5.3 | 7.2 | 44.4% | 1 | 1.76s | 972 | 61 | 0 | |
| Gemini 3 Flash Preview | 5.3 | 7.2 | 44.4% | 1 | 9.74s | 648 | 12 | 9,096 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 10.0 | 10.0 | 100.0% | 0 | 3.48s | 708 | 230 | 0 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 3.68s | 492 | 120 | 981 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 9.9 | 10.0 | 100.0% | 0 | 1.37s | 909 | 95 | 0 | |
| Gemini 3 Flash Preview | 9.9 | 10.0 | 100.0% | 0 | 7.02s | 621 | 71 | 2,752 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 7.7 | 10.0 | 66.7% | 0 | 2.74s | 894 | 783 | 0 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 5.77s | 562 | 288 | 3,168 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 10.0 | 10.0 | 100.0% | 0 | 5.35s | 11,775 | 355 | 0 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 4.99s | 5,550 | 234 | 415 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 3.0 | 10.0 | 0.0% | 0 | 3.41s | 258 | 212 | 0 | |
| Gemini 3 Flash Preview | 10.0 | 10.0 | 100.0% | 0 | 2.75s | 156 | 9 | 633 |
Quick Compare
Switch Comparison Pair
Gemini 3 Flash PreviewlowvsQwen3.5-122B-A10BmediumClaude Opus 4.8nonevsMuse Glimmer 30BlowClaude Opus 4.8nonevsGrok 4.6lowClaude Opus 4.8nonevsGemini 3.1 Flash LitemediumClaude Opus 4.8nonevsQwen3.5-122B-A10BmediumClaude Opus 4.8nonevsEmber-1highGemini 3 Flash PreviewlowvsKimi K2.7 CodemediumClaude Opus 4.8nonevsGemma 4 31BmediumFree AvailableClaude Opus 4.8nonevsGPT-5.6 LunalowClaude Opus 4.8nonevsEmber-1lowEmber-1highvsGemini 3 Flash PreviewlowGemini 3 Flash PreviewlowvsGPT-5.2 Chatnone