- Rank
- #111
- Total Output Tokens
- 203,134
- Response Time (avg)
- 55.99s
- Total Cost
- $0.261
DeepSeek V4 Flash 0423 (high) vs Kimi K3.1 Pro (high)
Kimi K3.1 Pro (high) leads on average score with 8.2 vs 8.1. DeepSeek V4 Flash 0423 (high) has the lower benchmark cost at $0.261 vs $1.646. Kimi K3.1 Pro (high) is faster at 54.31s vs 55.99s, with pass rates of 71.0% vs 79.7%.
Compared models
- Rank
- #107
- Total Output Tokens
- 114,612
- Response Time (avg)
- 54.31s
- Total Cost
- $1.646
Recommended model
DeepSeek V4 Flash 0423 (high)
Its score stays close to the best score here (8.1 vs 8.2), while costing about 6.3x less than Kimi K3.1 Pro (high).
Detailed comparison
| Metric | DeepSeek V4 Flash 0423 DeepSeek V4 Flash 0423 high | Kimi K3.1 Pro Kimi K3.1 Pro high |
|---|---|---|
| Score | 8.1 | 8.2 |
| Rank | #111 | #107 |
| Reliability | 10.0 | 8.5 |
| Consistency | 8.6 | 8.4 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 71.0% | 79.7% |
| Flaky tests | 4 | 5 |
| Total Runs | 69 | 69 |
| Cost per result | 0.547 | 10.288 |
| Total Cost | $0.261 | $1.646 |
| Input Price | $0.002 / 1M | $2.000 / 1M |
| Output Price | $1.280 / 1M | $10.000 / 1M |
| Cache Read Price | $0.002 / 1M | $0.200 / 1M |
| Cache Write Price | N/A | N/A |
| Total Input Tokens | 298,794 | 249,927 |
| Output Tokens | 45,873 | 10,175 |
| Reasoning Tokens | 188,721 | 104,437 |
| Response Time (avg) | 55.99s | 54.31s |
| Response Time (max) | 218.13s | 601.80s |
| Response Time (total) | 1287.87s | 1249.02s |
| Parameters | 284B total (13B active) | ~2.8T total (~104B active) |
| Availability | Open source | 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.
#111 DeepSeek V4 Flash 0423
high- Cost
- $0.003
- Time
- 93.1s
- Tokens
- 7,926 tok
#107 MoonshotAI: Kimi K3.1 Pro
high- Cost
- $0.074
- Time
- 141.9s
- Tokens
- 7,498 tok
Category Breakdown
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 10.0 | 10.0 | 100.0% | 0 | 148.13s | 190,314 | 8,644 | 14,640 | |
| Kimi K3.1 Pro | 7.4 | 3.8 | 66.7% | 1 | 93.37s | 138,832 | 2,133 | 3,989 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 8.3 | 10.0 | 75.0% | 0 | 28.51s | 540 | 140 | 7,770 | |
| Kimi K3.1 Pro | 10.0 | 10.0 | 100.0% | 0 | 6.91s | 1,650 | 562 | 2,282 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 7.8 | 10.0 | 66.7% | 0 | 50.60s | 7,279 | 395 | 34,862 | |
| Kimi K3.1 Pro | 10.0 | 10.0 | 100.0% | 0 | 24.94s | 8,070 | 464 | 9,637 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 6.4 | 5.8 | 66.7% | 1 | 104.10s | 82,663 | 4,633 | 37,533 | |
| Kimi K3.1 Pro | 4.6 | 2.7 | 33.3% | 2 | 36.74s | 80,954 | 5,564 | 3,489 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 10.0 | 10.0 | 100.0% | 0 | 28.03s | 7,290 | 201 | 1,179 | |
| Kimi K3.1 Pro | 10.0 | 10.0 | 100.0% | 0 | 4.83s | 7,845 | 273 | 541 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 3.6 | 7.2 | 22.2% | 1 | 115.42s | 754 | 22,778 | 79,643 | |
| Kimi K3.1 Pro | 5.3 | 7.2 | 44.4% | 1 | 274.56s | 1,324 | 131 | 66,591 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 6.1 | 3.1 | 66.7% | 1 | 25.15s | 471 | 79 | 632 | |
| Kimi K3.1 Pro | 10.0 | 10.0 | 100.0% | 0 | 8.92s | 735 | 171 | 800 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 10.0 | 10.0 | 100.0% | 0 | 15.36s | 627 | 63 | 1,622 | |
| Kimi K3.1 Pro | 10.0 | 10.0 | 100.0% | 0 | 5.71s | 1,185 | 147 | 1,029 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 8.2 | 7.2 | 88.9% | 1 | 26.11s | 594 | 196 | 1,767 | |
| Kimi K3.1 Pro | 8.2 | 7.2 | 88.9% | 1 | 8.23s | 1,425 | 325 | 2,477 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 10.0 | 10.0 | 100.0% | 0 | 74.73s | 8,079 | 228 | 542 | |
| Kimi K3.1 Pro | 10.0 | 10.0 | 100.0% | 0 | 11.68s | 7,439 | 348 | 228 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0423 | 3.0 | 10.0 | 0.0% | 0 | 54.46s | 183 | 8,516 | 8,531 | |
| Kimi K3.1 Pro | 3.0 | 10.0 | 0.0% | 0 | 89.65s | 468 | 57 | 13,374 |
Quick Compare
Switch Comparison Pair
Claude Opus 4.7mediumvsDeepSeek V4 Flash 0423highSeed-2.0-LitemediumvsKimi K3.1 ProhighSeed-2.0-CodelowvsKimi K3.1 ProhighKimi K3.1 ProhighvsGPT-5.6 TerramediumSeed-2.0-CodelowvsDeepSeek V4 Flash 0423highKimi K3.1 ProhighvsGLM 5.2mediumDeepSeek V4 Flash 0423highvsNemotron 3 UltramediumFree AvailableDeepSeek V4.1 Flash 1017maxvsKimi K3.1 ProhighGemini 4 ArgonlowvsKimi K3.1 ProhighKimi K3.1 ProhighvsQwen3.7 PlusmediumLing 3.1 FlashmediumvsKimi K3.1 ProhighDeepSeek V4 Flash 0423highvsGPT-5.4 Nanomedium