- Rank
- #96
- Total Output Tokens
- 67,522
- Response Time (avg)
- 16.72s
- Total Cost
- $3.490
Claude Opus 4.8 (medium) vs DeepSeek V4.1 Flash 1017 (max)
The average score is effectively tied at 8.3 vs 8.2. DeepSeek V4.1 Flash 1017 (max) has the lower benchmark cost at $0.757 vs $3.490. Claude Opus 4.8 (medium) is faster at 16.72s vs 78.20s, with pass rates of 82.6% vs 76.8%.
Compared models
- Rank
- #100
- Total Output Tokens
- 1,170,181
- Response Time (avg)
- 78.20s
- Total Cost
- $0.757
Recommended model
DeepSeek V4.1 Flash 1017 (max)
It has the best score here (8.2), while costing about 4.6x less than Claude Opus 4.8 (medium).
Detailed comparison
| Metric | Claude Opus 4.8 Claude Opus 4.8 medium | DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017 max |
|---|---|---|
| Score | 8.3 | 8.2 |
| Rank | #96 | #100 |
| Reliability | 10.0 | 10.0 |
| Consistency | 9.0 | 8.2 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 82.6% | 76.8% |
| Flaky tests | 3 | 5 |
| Total Runs | 69 | 69 |
| Cost per result | 20.527 | 5.041 |
| Total Cost | $3.490 | $0.757 |
| Input Price | $5.000 / 1M | $0.150 / 1M |
| Output Price | $25.000 / 1M | $0.600 / 1M |
| Cache Read Price | $0.500 / 1M | $0.003 / 1M |
| Cache Write Price | $6.250 / 1M | N/A |
| Total Input Tokens | 360,294 | 360,065 |
| Output Tokens | 43,441 | 7,711 |
| Reasoning Tokens | 24,401 | 1,162,470 |
| Response Time (avg) | 16.72s | 78.20s |
| Response Time (max) | 99.37s | 605.14s |
| Response Time (total) | 384.66s | 1798.65s |
| Parameters | ~5T total (~500B active) | ~748B total (~16B active) |
| Availability | Closed | Open source |
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.
#96 Claude Opus 4.8
medium- Cost
- $0.057
- Time
- 23.1s
- Tokens
- 2,412 tok
#100 DeepSeek V4.1 Flash 1017
max- Cost
- $0.018
- Time
- 135.0s
- Tokens
- 35,163 tok
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 | 6.1 | 3.1 | 66.7% | 1 | 99.37s | 221,846 | 2,676 | 13,239 | |
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 45.58s | 139,675 | 1,771 | 5,358 |
| 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 | 3.95s | 834 | 1,179 | 478 | |
| DeepSeek V4.1 Flash 1017 | 8.3 | 10.0 | 75.0% | 0 | 4.16s | 852 | 193 | 6,178 |
| Coding | 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 | 15.33s | 10,590 | 9,945 | 1,381 | |
| DeepSeek V4.1 Flash 1017 | 5.6 | 4.2 | 66.7% | 2 | 199.23s | 7,509 | 111 | 475,423 |
| 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 | 54.29s | 101,005 | 19,531 | 4,762 | |
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 104.92s | 192,579 | 4,716 | 125,203 |
| 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 | 7.1 | 5.6 | 83.3% | 1 | 12.29s | 10,503 | 481 | 312 | |
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 1.99s | 7,446 | 207 | 1,323 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 3.6 | 7.2 | 22.2% | 1 | 18.11s | 972 | 7,476 | 2,987 | |
| DeepSeek V4.1 Flash 1017 | 5.9 | 7.2 | 55.6% | 1 | 260.29s | 909 | 11 | 487,376 |
| 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 | 2.46s | 708 | 237 | 0 | |
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 3.52s | 549 | 128 | 1,020 |
| Instructions following | 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 | 3.32s | 909 | 373 | 320 | |
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 1.73s | 783 | 69 | 1,223 |
| 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 | 3.95s | 894 | 791 | 483 | |
| DeepSeek V4.1 Flash 1017 | 6.3 | 4.9 | 66.7% | 2 | 12.29s | 828 | 247 | 17,864 |
| 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 | 8.96s | 11,775 | 301 | 225 | |
| DeepSeek V4.1 Flash 1017 | 10.0 | 10.0 | 100.0% | 0 | 2.43s | 8,674 | 237 | 349 |
| 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 | 6.14s | 258 | 451 | 214 | |
| DeepSeek V4.1 Flash 1017 | 3.0 | 10.0 | 0.0% | 0 | 97.77s | 261 | 21 | 41,153 |
Quick Compare
Switch Comparison Pair
DeepSeek V4.1 Flash 1017maxvsGemini 4 ArgonlowDeepSeek V4.1 Flash 1017maxvsGrok 4.5highDeepSeek V4.1 Flash 1017maxvsGLM 5.2mediumDeepSeek V4.1 Flash 1017maxvsQwen3.7 PlusmediumDeepSeek V4.1 Flash 1017maxvsLing 3.1 FlashmediumDeepSeek V4.1 Flash 1017maxvsGPT-5.6 TerramediumClaude Opus 4.8mediumvsGemini 4 ArgonlowDeepSeek V4.1 Flash 1017maxvsGPT-6 LunamediumClaude Opus 4.8mediumvsGrok 4.5highClaude Opus 4.8mediumvsKimi K3maxClaude Opus 4.8mediumvsGemini 3.5 FlashhighClaude Opus 4.8mediumvsGPT-5.6 Terrahigh