- Rank
- #81
- Total Output Tokens
- 919,699
- Response Time (avg)
- 61.71s
- Total Cost
- $0.509
Claude Haiku 5.5 (max) vs DeepSeek V4 Flash 0731 (high)
Claude Haiku 5.5 (max) leads on average score with 8.5 vs 8.4. Claude Haiku 5.5 (max) has the lower benchmark cost at $0.509 vs $0.576. Claude Haiku 5.5 (max) is faster at 61.71s vs 118.83s, with pass rates of 85.5% vs 76.8%.
Compared models
- Rank
- #89
- Total Output Tokens
- 448,665
- Response Time (avg)
- 118.83s
- Total Cost
- $0.576
Recommended model
Claude Haiku 5.5 (max)
It has the best score here (8.5), while responding about 1.9x faster than DeepSeek V4 Flash 0731 (high).
Detailed comparison
| Metric | Claude Haiku 5.5 Claude Haiku 5.5 max | DeepSeek V4 Flash 0731 DeepSeek V4 Flash 0731 high |
|---|---|---|
| Score | 8.5 | 8.4 |
| Rank | #81 | #89 |
| Reliability | 10.0 | 10.0 |
| Consistency | 9.6 | 8.1 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 85.5% | 76.8% |
| Flaky tests | 1 | 5 |
| Total Runs | 69 | 69 |
| Cost per result | 2.677 | 1.069 |
| Total Cost | $0.509 | $0.576 |
| Input Price | $0.100 / 1M | $0.005 / 1M |
| Output Price | $0.500 / 1M | $1.280 / 1M |
| Cache Read Price | $0.010 / 1M | $0.005 / 1M |
| Cache Write Price | $0.125 / 1M | N/A |
| Total Input Tokens | 487,516 | 281,863 |
| Output Tokens | 10,212 | 24,535 |
| Reasoning Tokens | 909,487 | 507,976 |
| Response Time (avg) | 61.71s | 118.83s |
| Response Time (max) | 288.94s | 600.61s |
| Response Time (total) | 1419.40s | 2733.01s |
| Parameters | ~50B | 284B total (13B 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.
#81 Claude Haiku 5.5
max
OpenRouter returned no showcase content (finish_reason: error).
- Cost
- $0.000
- Time
- 164.5s
- Tokens
- 0 tok
#89 DeepSeek V4 Flash 0731
high
No output was saved. The original provider response or failure reason is unavailable.
- Cost
- $0.000
- Time
- 187.3s
- Tokens
- 19,048 tok
Category Breakdown
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 4.7 | 1.6 | 66.7% | 1 | 93.30s | 349,997 | 2,345 | 42,315 | |
| DeepSeek V4 Flash 0731 | 10.0 | 10.0 | 100.0% | 0 | 204.36s | 185,161 | 7,569 | 11,635 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 10.0 | 10.0 | 100.0% | 0 | 5.52s | 858 | 401 | 10,159 | |
| DeepSeek V4 Flash 0731 | 8.7 | 7.9 | 91.7% | 1 | 13.62s | 1,488 | 542 | 10,576 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 10.0 | 10.0 | 100.0% | 0 | 55.87s | 10,608 | 532 | 125,988 | |
| DeepSeek V4 Flash 0731 | 6.3 | 6.3 | 55.6% | 1 | 252.67s | 7,044 | 2,160 | 191,210 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 10.0 | 10.0 | 100.0% | 0 | 148.38s | 99,980 | 4,909 | 215,518 | |
| DeepSeek V4 Flash 0731 | 10.0 | 10.0 | 100.0% | 0 | 87.10s | 67,283 | 11,903 | 41,397 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 10.0 | 10.0 | 100.0% | 0 | 11.11s | 10,515 | 311 | 13,476 | |
| DeepSeek V4 Flash 0731 | 10.0 | 10.0 | 100.0% | 0 | 3.65s | 7,764 | 336 | 1,259 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 5.3 | 10.0 | 33.3% | 0 | 228.16s | 990 | 18 | 426,269 | |
| DeepSeek V4 Flash 0731 | 3.5 | 4.4 | 33.3% | 2 | 458.65s | 700 | 104 | 215,629 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 10.0 | 10.0 | 100.0% | 0 | 42.22s | 714 | 250 | 26,083 | |
| DeepSeek V4 Flash 0731 | 10.0 | 10.0 | 100.0% | 0 | 5.64s | 708 | 72 | 533 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 10.0 | 10.0 | 100.0% | 0 | 6.22s | 921 | 99 | 5,965 | |
| DeepSeek V4 Flash 0731 | 9.8 | 10.0 | 100.0% | 0 | 4.46s | 1,101 | 119 | 939 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 10.0 | 10.0 | 100.0% | 0 | 16.54s | 912 | 716 | 29,419 | |
| DeepSeek V4 Flash 0731 | 8.2 | 7.7 | 77.8% | 1 | 9.36s | 1,305 | 397 | 6,801 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 10.0 | 10.0 | 100.0% | 0 | 9.86s | 11,757 | 355 | 3,989 | |
| DeepSeek V4 Flash 0731 | 10.0 | 10.0 | 100.0% | 0 | 5.42s | 8,889 | 357 | 451 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 3.0 | 10.0 | 0.0% | 0 | 18.80s | 264 | 276 | 10,306 | |
| DeepSeek V4 Flash 0731 | 3.0 | 10.0 | 0.0% | 0 | 110.63s | 420 | 976 | 27,546 |
Quick Compare
Switch Comparison Pair
Claude Haiku 5.5maxvsQwen3.7 MaxmediumClaude Haiku 5.5maxvsMuse Spark 1.3lowDeepSeek V4 Flash 0731highvsGemini 3.1 Pro PreviewmediumClaude Haiku 5.5maxvsGrok 4.6highClaude Haiku 5.5maxvsNemotron 3.5 Super VLhighFree AvailableDeepSeek V4 Flash 0731highvsMuse Glimmer 30BxhighDeepSeek V4 Flash 0731highvsGPT-5 MinimediumClaude Haiku 5.5maxvsQwen3.8 2.4T A95BlowDeepSeek V4 Flash 0731highvsQwen3.8 2.4T A95BlowClaude Haiku 5.5maxvsGPT-5 MinimediumClaude Haiku 5.5maxvsMuse Glimmer 30BxhighClaude Haiku 5.5maxvsGemini 3.1 Pro Previewmedium