- Rank
- #109
- Total Output Tokens
- 371,547
- Response Time (avg)
- 28.04s
- Total Cost
- $0.494
DeepSeek V4.1 Flash (low) vs DeepSeek V4 Pro 0423 (high)
The average score is effectively tied at 8.0 vs 8.1. DeepSeek V4 Pro 0423 (high) has the lower benchmark cost at $0.149 vs $0.494. DeepSeek V4.1 Flash (low) is faster at 28.04s vs 91.29s, with pass rates of 73.9% vs 65.2%.
Compared models
- Rank
- #106
- Total Output Tokens
- 211,343
- Response Time (avg)
- 91.29s
- Total Cost
- $0.149
Recommended model
DeepSeek V4 Pro 0423 (high)
It has the best score here (8.1), while costing about 3.3x less than DeepSeek V4.1 Flash (low).
Detailed comparison
| Metric | DeepSeek V4.1 Flash DeepSeek V4.1 Flash low | DeepSeek V4 Pro 0423 DeepSeek V4 Pro 0423 high |
|---|---|---|
| Score | 8.0 | 8.1 |
| Rank | #109 | #106 |
| Reliability | 9.6 | 10.0 |
| Consistency | 8.7 | 7.8 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 73.9% | 65.2% |
| Flaky tests | 4 | 6 |
| Total Runs | 69 | 69 |
| Cost per result | 1.576 | 3.717 |
| Total Cost | $0.494 | $0.149 |
| Input Price | $0.013 / 1M | $0.209 / 1M |
| Output Price | $1.320 / 1M | $0.418 / 1M |
| Cache Read Price | $0.013 / 1M | $0.018 / 1M |
| Cache Write Price | N/A | N/A |
| Total Input Tokens | 266,849 | 287,061 |
| Output Tokens | 8,284 | 32,056 |
| Reasoning Tokens | 363,263 | 196,607 |
| Response Time (avg) | 28.04s | 91.29s |
| Response Time (max) | 149.84s | 416.76s |
| Response Time (total) | 645.03s | 2099.56s |
| Parameters | 748B total (16B active) | 1.6T total (49B active) |
| Availability | Open source | 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.
#109 DeepSeek V4.1 Flash
low- Cost
- $0.017
- Time
- 43.6s
- Tokens
- 14,069 tok
#106 DeepSeek V4 Pro 0423
high- Cost
- $0.023
- Time
- 257.6s
- Tokens
- 14,870 tok
Category Breakdown
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 6.1 | 3.1 | 66.7% | 1 | 56.02s | 167,134 | 1,903 | 21,681 | |
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 64.54s | 196,304 | 9,128 | 10,091 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 8.3 | 10.0 | 75.0% | 0 | 3.32s | 852 | 171 | 4,328 | |
| DeepSeek V4 Pro 0423 | 5.7 | 5.9 | 58.3% | 2 | 25.70s | 536 | 149 | 3,214 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 40.66s | 7,509 | 378 | 81,978 | |
| DeepSeek V4 Pro 0423 | 6.3 | 8.7 | 33.3% | 0 | 243.00s | 5,090 | 383 | 84,580 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 24.73s | 77,368 | 4,906 | 24,016 | |
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 78.99s | 66,082 | 4,582 | 25,404 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 6.5 | 10.0 | 50.0% | 0 | 3.80s | 2,397 | 120 | 1,149 | |
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 25.03s | 7,690 | 274 | 2,166 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 3.5 | 4.4 | 33.3% | 2 | 95.58s | 909 | 27 | 184,701 | |
| DeepSeek V4 Pro 0423 | 3.6 | 7.2 | 22.2% | 1 | 249.47s | 578 | 16,870 | 58,188 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 4.34s | 549 | 117 | 1,319 | |
| DeepSeek V4 Pro 0423 | 10.0 | 10.0 | 100.0% | 0 | 8.83s | 471 | 115 | 1,013 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 8.38s | 783 | 63 | 1,546 | |
| DeepSeek V4 Pro 0423 | 7.8 | 6.6 | 83.3% | 1 | 8.73s | 627 | 66 | 2,726 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 8.2 | 7.7 | 77.8% | 1 | 9.39s | 828 | 273 | 14,502 | |
| DeepSeek V4 Pro 0423 | 6.9 | 4.9 | 77.8% | 2 | 56.85s | 591 | 178 | 2,563 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 13.83s | 8,259 | 313 | 284 | |
| DeepSeek V4 Pro 0423 | 9.8 | 10.0 | 100.0% | 0 | 15.92s | 8,909 | 295 | 701 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 3.0 | 10.0 | 0.0% | 0 | 46.86s | 261 | 13 | 27,759 | |
| DeepSeek V4 Pro 0423 | 3.0 | 10.0 | 0.0% | 0 | 34.01s | 183 | 16 | 5,961 |
Quick Compare
Switch Comparison Pair
Claude Opus 4.7mediumvsDeepSeek V4 Pro 0423highClaude Opus 4.7mediumvsDeepSeek V4.1 FlashlowDeepSeek V4.1 FlashlowvsGPT-5.6 LunahighDeepSeek V4.1 FlashlowvsNemotron 3 UltramediumFree AvailableSeed-2.0-CodelowvsDeepSeek V4 Pro 0423highDeepSeek V4.1 FlashlowvsGPT-5.4 NanomediumDeepSeek V4.1 FlashlowvsGemini 3.8 FlashmediumSeed-2.0-LitemediumvsDeepSeek V4 Pro 0423highDeepSeek V4 Pro 0423highvsNemotron 3 UltramediumFree AvailableDeepSeek V4.1 FlashlowvsQwen3.5-27BmediumDeepSeek V4.1 FlashlowvsGLM 5.3 FlashXmaxClaude Fable 5.1highvsDeepSeek V4.1 Flashlow