- Rank
- #181
- Total Output Tokens
- 96,782
- Response Time (avg)
- 14.84s
- Total Cost
- $0.000
Minimax M3.1 Flash (low) vs Kimi K2.7 Code (medium)
Minimax M3.1 Flash (low) leads on average score with 7.1 vs 7.0. Minimax M3.1 Flash (low) has the lower benchmark cost at $0.000 vs $1.136. Minimax M3.1 Flash (low) is faster at 14.84s vs 81.18s, with pass rates of 55.1% vs 60.9%.
Compared models
- Rank
- #187
- Total Output Tokens
- 207,661
- Response Time (avg)
- 81.18s
- Total Cost
- $1.136
Recommended model
Minimax M3.1 Flash (low)
It has the best score here (7.1), while responding about 5.5x faster than Kimi K2.7 Code (medium).
Detailed comparison
| Metric | Minimax M3.1 Flash Minimax M3.1 Flash low Free Available | Kimi K2.7 Code Kimi K2.7 Code medium |
|---|---|---|
| Score | 7.1 | 7.0 |
| Rank | #181 | #187 |
| Reliability | 10.0 | 10.0 |
| Consistency | 9.6 | 8.1 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 55.1% | 60.9% |
| Flaky tests | 1 | 5 |
| Total Runs | 69 | 69 |
| Cost per result | 0.000 | 8.755 |
| Total Cost | $0.000 | $1.136 |
| Input Price | $0.000 / 1M | $0.672 / 1M |
| Output Price | $0.000 / 1M | $3.350 / 1M |
| Cache Read Price | N/A | $0.180 / 1M |
| Cache Write Price | N/A | N/A |
| Total Input Tokens | 285,795 | 245,179 |
| Output Tokens | 10,087 | 62,697 |
| Reasoning Tokens | 86,695 | 196,621 |
| Response Time (avg) | 14.84s | 81.18s |
| Response Time (max) | 133.79s | 365.80s |
| Response Time (total) | 341.25s | 1785.87s |
| Parameters | - | 1T total (32B active) |
| Availability | Closed | Weights available |
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.
#181 Minimax M3.1 Flash
low- Cost
- $0.000
- Time
- 18.4s
- Tokens
- 3,268 tok
#187 MoonshotAI: Kimi K2.7 Code
medium- Cost
- $0.025
- Time
- 138.0s
- Tokens
- 6,093 tok
Category Breakdown
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Minimax M3.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 51.50s | 149,924 | 1,535 | 7,029 | |
| Kimi K2.7 Code | 5.0 | 10.0 | 0.0% | 0 | 104.02s | 173,094 | 5,244 | 14,528 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Minimax M3.1 Flash | 6.5 | 10.0 | 50.0% | 0 | 1.76s | 2,838 | 114 | 1,156 | |
| Kimi K2.7 Code | 7.3 | 5.8 | 83.3% | 2 | 11.56s | 618 | 3,048 | 5,041 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Minimax M3.1 Flash | 5.7 | 9.7 | 33.3% | 0 | 8.98s | 9,024 | 393 | 8,526 | |
| Kimi K2.7 Code | 7.8 | 9.3 | 66.7% | 0 | 146.73s | 4,650 | 1,864 | 25,635 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Minimax M3.1 Flash | 7.2 | 5.8 | 83.3% | 1 | 20.57s | 103,379 | 7,285 | 10,237 | |
| Kimi K2.7 Code | 7.3 | 5.8 | 83.3% | 1 | 66.03s | 57,353 | 3,642 | 21,308 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Minimax M3.1 Flash | 6.5 | 10.0 | 50.0% | 0 | 806ms | 2,802 | 111 | 222 | |
| Kimi K2.7 Code | 10.0 | 10.0 | 100.0% | 0 | 12.27s | 7,014 | 248 | 2,569 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Minimax M3.1 Flash | 7.7 | 10.0 | 66.7% | 0 | 53.28s | 2,400 | 18 | 46,584 | |
| Kimi K2.7 Code | 3.7 | 6.5 | 22.2% | 1 | 184.17s | 443 | 29,311 | 66,939 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Minimax M3.1 Flash | 5.1 | 10.0 | 0.0% | 0 | 3.19s | 1,032 | 90 | 561 | |
| Kimi K2.7 Code | 10.0 | 10.0 | 100.0% | 0 | 10.78s | 477 | 1,024 | 1,071 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Minimax M3.1 Flash | 6.3 | 10.0 | 50.0% | 0 | 1.60s | 1,779 | 58 | 419 | |
| Kimi K2.7 Code | 9.9 | 10.0 | 100.0% | 0 | 5.39s | 669 | 725 | 1,232 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Minimax M3.1 Flash | 7.7 | 10.0 | 66.7% | 0 | 2.12s | 2,313 | 173 | 963 | |
| Kimi K2.7 Code | 5.9 | 7.7 | 44.4% | 1 | 41.00s | 651 | 15,438 | 17,368 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Minimax M3.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 2.76s | 9,551 | 297 | 62 | |
| Kimi K2.7 Code | 3.0 | 10.0 | 0.0% | 0 | 0ms | 0 | 0 | 0 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Minimax M3.1 Flash | 3.0 | 10.0 | 0.0% | 0 | 37.65s | 753 | 13 | 10,936 | |
| Kimi K2.7 Code | 3.0 | 10.0 | 0.0% | 0 | 341.76s | 210 | 2,153 | 40,930 |
Quick Compare
Switch Comparison Pair
Minimax M3.1 FlashlowFree AvailablevsGLM 5.3 FlashXmediumMinimax M3.1 FlashlowFree AvailablevsMiMo-V2.5mediumEmber-1lowvsKimi K2.7 CodemediumKimi K2.7 CodemediumvsGPT-5.2 ChatdefaultKimi K2.7 CodemediumvsStep 5 PreviewhighMinimax M3.1 FlashlowFree AvailablevsQwen3.8 Flash NextxhighKimi K2.7 CodemediumvsGrok 4.6lowMinimax M3.1 FlashlowFree AvailablevsGPT-5.2 ChatdefaultGemini 3 Flash PreviewlowvsKimi K2.7 CodemediumMuse Glimmer 30BlowvsKimi K2.7 CodemediumMinimax M3.1 FlashmaxFree AvailablevsKimi K2.7 CodemediumGemini 3.1 Flash Lite PreviewmediumvsMinimax M3.1 FlashlowFree Available