- Rank
- #167
- Total Output Tokens
- 24,343
- Response Time (avg)
- 7.54s
- Total Cost
- $2.334
Claude Opus 4.8 vs Mercury 2.5 Preview (medium)
The average score is effectively tied at 6.9 vs 6.8. Mercury 2.5 Preview (medium) has the lower benchmark cost at $0.037 vs $2.334. Mercury 2.5 Preview (medium) is faster at 6.66s vs 7.54s, with pass rates of 60.9% vs 66.7%.
Compared models
- Rank
- #171
- Total Output Tokens
- 150,107
- Response Time (avg)
- 6.66s
- Total Cost
- $0.037
Recommended model
Mercury 2.5 Preview (medium)
It has the best score here (6.8), while costing about 63.8x less than Claude Opus 4.8.
Detailed comparison
| Metric | Claude Opus 4.8 Claude Opus 4.8 none | Mercury 2.5 Preview Mercury 2.5 Preview medium |
|---|---|---|
| Score | 6.9 | 6.8 |
| Rank | #167 | #171 |
| Reliability | 10.0 | 10.0 |
| Consistency | 9.3 | 9.6 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 60.9% | 66.7% |
| Flaky tests | 2 | 1 |
| Total Runs | 69 | 69 |
| Cost per result | 17.953 | 0.244 |
| Total Cost | $2.334 | $0.037 |
| Input Price | $5.000 / 1M | $0.000 / 1M |
| Output Price | $25.000 / 1M | $0.000 / 1M |
| Total Input Tokens | 345,059 | 397,291 |
| Output Tokens | 24,343 | 6,355 |
| Reasoning Tokens | 0 | 143,752 |
| Response Time (avg) | 7.54s | 6.66s |
| Response Time (max) | 65.07s | 74.63s |
| Response Time (total) | 173.31s | 153.29s |
| Parameters | ~5T total (~500B active) | ~100B |
| Availability | Closed | Closed |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#167 Claude Opus 4.8
none- Cost
- $0.053
- Time
- 22.0s
- Tokens
- 2,253 tok
#171 Mercury 2.5 Preview
medium- Cost
- $0.001
- Time
- 2.7s
- Tokens
- 2,241 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 | 5.0 | 10.0 | 0.0% | 0 | 65.07s | 195,856 | 7,546 | 0 | |
| Mercury 2.5 Preview | 3.9 | 9.6 | 0.0% | 0 | 74.63s | 284,578 | 919 | 22,154 |
| 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 | |
| Mercury 2.5 Preview | 10.0 | 10.0 | 100.0% | 0 | 1.43s | 781 | 203 | 7,921 |
| 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 | |
| Mercury 2.5 Preview | 7.8 | 10.0 | 66.7% | 0 | 3.86s | 7,839 | 552 | 22,126 |
| 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 | |
| Mercury 2.5 Preview | 6.5 | 10.0 | 50.0% | 0 | 13.86s | 92,663 | 3,607 | 41,588 |
| 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 | |
| Mercury 2.5 Preview | 10.0 | 10.0 | 100.0% | 0 | 2.77s | 8,292 | 514 | 11,354 |
| 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 | |
| Mercury 2.5 Preview | 5.3 | 7.2 | 44.4% | 1 | 3.72s | 853 | 62 | 17,120 |
| 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 | |
| Mercury 2.5 Preview | 5.0 | 10.0 | 0.0% | 0 | 2.09s | 538 | 99 | 3,375 |
| 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 | |
| Mercury 2.5 Preview | 9.8 | 10.0 | 100.0% | 0 | 1.35s | 744 | 96 | 3,987 |
| 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 | |
| Mercury 2.5 Preview | 10.0 | 10.0 | 100.0% | 0 | 1.87s | 771 | 274 | 7,323 |
| 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 | |
| Mercury 2.5 Preview | 3.0 | 10.0 | 0.0% | 0 | 2.37s | 0 | 0 | 0 |
| 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 | |
| Mercury 2.5 Preview | 3.0 | 10.0 | 0.0% | 0 | 4.13s | 232 | 29 | 6,804 |
Quick Compare
Switch Comparison Pair
Mercury 2.5 PreviewmediumvsInklinglowFree AvailableClaude Opus 4.8nonevsGPT-5.6 LunalowClaude Opus 4.8nonevsGemma 4 31BmediumFree AvailableMercury 2.5 PreviewmediumvsGPT-6 SolnoneClaude Opus 4.8nonevsEmber-1highClaude Opus 4.8nonevsKimi K2.6mediumClaude Opus 4.8nonevsGemini 3.1 Flash LitemediumClaude Opus 4.8nonevsQwen3.5-FlashmediumClaude Opus 4.8nonevsInklinglowFree AvailableClaude Sonnet 5.5lowvsMercury 2.5 PreviewmediumMercury 2.5 PreviewmediumvsGPT-5.6 LunalowEmber-1highvsMercury 2.5 Previewmedium