- Rank
- #103
- Total Output Tokens
- 52,237
- Response Time (avg)
- 12.88s
- Total Cost
- $2.089
Claude Opus 4.8 (low) vs Claude Sonnet 4.6 (medium)
Claude Sonnet 4.6 (medium) leads on average score with 7.8 vs 7.8. Claude Opus 4.8 (low) has the lower benchmark cost at $2.089 vs $2.126. Claude Opus 4.8 (low) is faster at 12.88s vs 28.08s, with pass rates of 80.3% vs 65.2%.
Compared models
- Rank
- #100
- Total Output Tokens
- 120,427
- Response Time (avg)
- 28.08s
- Total Cost
- $2.126
Recommended model
Claude Opus 4.8 (low)
Its score stays close to the best score here (7.8 vs 7.8), while responding about 2.2x faster than Claude Sonnet 4.6 (medium).
Detailed comparison
| Metric | Claude Opus 4.8 Claude Opus 4.8 low | Claude Sonnet 4.6 Claude Sonnet 4.6 medium |
|---|---|---|
| Score | 7.8 | 7.8 |
| Rank | #103 | #100 |
| Reliability | 10.0 | 10.0 |
| Consistency | 8.9 | 9.5 |
| Attempts | 66/66 | 66/66 |
| Tests Correct | ||
| Attempt pass rate | 80.3% | 65.2% |
| Flaky tests | 3 | 1 |
| Total Runs | 66 | 66 |
| Cost per result | 13.054 | 15.182 |
| Total Cost | $2.089 | $2.126 |
| Input Price | $5.000 / 1M | $3.000 / 1M |
| Output Price | $25.000 / 1M | $15.000 / 1M |
| Total Input Tokens | 156,522 | 106,316 |
| Output Tokens | 43,056 | 79,338 |
| Reasoning Tokens | 9,181 | 41,089 |
| Response Time (avg) | 12.88s | 28.08s |
| Response Time (max) | 127.97s | 140.96s |
| Response Time (total) | 283.32s | 421.15s |
| Parameters | ~5T total (~500B active) | ~1T total (~100B active) |
| Availability | Closed | Closed |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#103 Claude Opus 4.8
low- Cost
- $0.031
- Time
- 14.1s
- Tokens
- 1,345 tok
#100 Claude Sonnet 4.6
medium
Reached the allocated time limit (300 seconds) without receiving showcase output.
- Cost
- $0.000
- Time
- 300.0s
- Tokens
- 0 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 4.8 | 10.0 | 10.0 | 100.0% | 0 | 3.30s | 834 | 793 | 371 | |
| Claude Sonnet 4.6 | 6.5 | 10.0 | 50.0% | 0 | 2.98s | 789 | 1,046 | 1,093 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 6.6 | 4.6 | 77.8% | 2 | 7.58s | 10,590 | 3,637 | 809 | |
| Claude Sonnet 4.6 | 5.7 | 6.6 | 44.4% | 1 | 33.29s | 6,995 | 16,089 | 3,686 |
| Combined | 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 | 36.87s | 119,079 | 13,586 | 2,867 | |
| Claude Sonnet 4.6 | 10.0 | 10.0 | 100.0% | 0 | 93.65s | 75,531 | 31,916 | 9,109 |
| 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 | 6.3 | 5.8 | 66.7% | 1 | 2.27s | 10,503 | 310 | 0 | |
| Claude Sonnet 4.6 | 10.0 | 10.0 | 100.0% | 0 | 13.90s | 8,676 | 649 | 742 |
| 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 | 10.0 | 33.3% | 0 | 46.54s | 972 | 23,226 | 4,472 | |
| Claude Sonnet 4.6 | 3.0 | 10.0 | 0.0% | 0 | 58.37s | 495 | 24,380 | 22,891 |
| 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 | 2.55s | 708 | 231 | 0 | |
| Claude Sonnet 4.6 | 10.0 | 10.0 | 100.0% | 0 | 4.94s | 564 | 256 | 433 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 9.8 | 10.0 | 100.0% | 0 | 2.78s | 909 | 111 | 221 | |
| Claude Sonnet 4.6 | 10.0 | 10.0 | 100.0% | 0 | 2.61s | 792 | 318 | 552 |
| Puzzle Solving | 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 | 3.01s | 894 | 592 | 184 | |
| Claude Sonnet 4.6 | 10.0 | 10.0 | 100.0% | 0 | 5.31s | 816 | 592 | 646 |
| 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 | 6.85s | 11,775 | 370 | 35 | |
| Claude Sonnet 4.6 | 10.0 | 10.0 | 100.0% | 0 | 7.48s | 11,454 | 655 | 351 |
| 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 | 5.48s | 258 | 200 | 222 | |
| Claude Sonnet 4.6 | 3.0 | 10.0 | 0.0% | 0 | 30.09s | 204 | 3,437 | 1,586 |
Quick Compare
Switch Comparison Pair
Claude Opus 4.8lowvsSeed-2.0-LitemediumClaude Opus 4.8lowvsQwen3.7 FlashhighClaude Opus 4.8lowvsQwen3.8 27BmediumClaude Opus 4.8lowvsGLM 5mediumClaude Sonnet 4.6mediumvsQwen3.8 27BlowClaude Sonnet 4.6mediumvsQwen3.7 FlashhighClaude Opus 4.8lowvsGPT-5.6 TerramediumClaude Opus 4.8lowvsGLM 5.2mediumClaude Opus 4.8lowvsGemini 3.5 Flash LitemediumClaude Sonnet 4.6mediumvsGPT-5.2 ChatnoneClaude Opus 4.8lowvsQwen3.6 PlusmediumClaude Sonnet 4.6mediumvsKimi K3max