- Rank
- #273
- Total Output Tokens
- 1,818,271
- Response Time (avg)
- 140.39s
- Total Cost
- $0.000
North Mini Code (medium) vs Hy4 preview (low)
The average score is effectively tied at 5.4 vs 5.4. North Mini Code (medium) has the lower benchmark cost at $0.000 vs $1.670. North Mini Code (medium) is faster at 140.39s vs 207.21s, with pass rates of 42.0% vs 21.7%.
Compared models
- Rank
- #274
- Total Output Tokens
- 687,477
- Response Time (avg)
- 207.21s
- Total Cost
- $1.670
Recommended model
Hy4 preview (low)
It has the strongest score in this comparison (5.4) and the best overall balance of cost and response time across all 2 models.
Detailed comparison
| Metric | North Mini Code North Mini Code medium Free Available | Hy4 preview Hy4 preview low |
|---|---|---|
| Score | 5.4 | 5.4 |
| Rank | #273 | #274 |
| Reliability | 8.9 | 6.5 |
| Consistency | 8.6 | 8.2 |
| Attempts | 61/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 42.0% | 21.7% |
| Flaky tests | 4 | 4 |
| Total Runs | 61 | 69 |
| Cost per result | 0.000 | 61.455 |
| Total Cost | $0.000 | $1.670 |
| Input Price | $0.000 / 1M | $0.751 / 1M |
| Output Price | $0.000 / 1M | $2.251 / 1M |
| Total Input Tokens | 166,347 | 162,180 |
| Output Tokens | 423,884 | 5,030 |
| Reasoning Tokens | 1,394,387 | 682,447 |
| Response Time (avg) | 140.39s | 207.21s |
| Response Time (max) | 786.72s | 597.45s |
| Response Time (total) | 3229.07s | 4765.91s |
| Parameters | 30B total (3B active) | 770B total (49B active) |
| Availability | Open source | Open source |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#273 North Mini Code
medium- Cost
- $0.000
- Time
- 51.8s
- Tokens
- 12,460 tok
#274 Hy4 preview
low
Provider returned error
- Cost
- $0.000
- Time
- 1.1s
- Tokens
- 0 tok
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Category Breakdown
| Agentic | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| North Mini Code | 3.9 | 9.6 | 0.0% | 0 | 105.20s | 84,605 | 0 | 53,480 | |
| Hy4 preview | 4.7 | 1.6 | 66.7% | 1 | 52.36s | 117,026 | 1,008 | 3,931 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| North Mini Code | 8.4 | 10.0 | 75.0% | 0 | 64.79s | 324 | 64,441 | 68,535 | |
| Hy4 preview | 6.0 | 8.9 | 0.0% | 0 | 129.60s | 624 | 478 | 72,022 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| North Mini Code | 4.5 | 4.9 | 33.3% | 2 | 320.43s | 7,119 | 219,891 | 561,569 | |
| Hy4 preview | 5.2 | 8.6 | 0.0% | 0 | 219.15s | 6,110 | 135 | 96,407 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| North Mini Code | 2.9 | 5.8 | 16.7% | 1 | 554.89s | 63,682 | 0 | 472,040 | |
| Hy4 preview | 2.9 | 5.8 | 16.7% | 1 | 139.43s | 28,254 | 2,485 | 8,420 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| North Mini Code | 10.0 | 10.0 | 100.0% | 0 | 24.06s | 6,819 | 240 | 2,659 | |
| Hy4 preview | 8.7 | 10.0 | 50.0% | 0 | 88.53s | 7,197 | 195 | 18,424 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| North Mini Code | 2.9 | 7.2 | 11.1% | 1 | 107.19s | 550 | 7,595 | 102,957 | |
| Hy4 preview | 4.5 | 10.0 | 0.0% | 0 | 470.24s | 716 | 28 | 220,446 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| North Mini Code | 5.1 | 10.0 | 0.0% | 0 | 25.08s | 444 | 1,546 | 1,635 | |
| Hy4 preview | 7.5 | 10.0 | 0.0% | 0 | 110.43s | 525 | 170 | 13,806 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| North Mini Code | 9.8 | 10.0 | 100.0% | 0 | 15.43s | 379 | 909 | 1,339 | |
| Hy4 preview | 9.8 | 10.0 | 100.0% | 0 | 77.72s | 732 | 71 | 17,054 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| North Mini Code | 3.3 | 10.0 | 0.0% | 0 | 19.70s | 543 | 2,215 | 2,485 | |
| Hy4 preview | 5.3 | 5.0 | 33.3% | 2 | 238.03s | 750 | 454 | 103,707 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| North Mini Code | 10.0 | 10.0 | 100.0% | 0 | 3.93s | 1,776 | 41 | 563 | |
| Hy4 preview | 3.0 | 10.0 | 0.0% | 0 | 93.67s | 0 | 0 | 0 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| North Mini Code | 3.0 | 10.0 | 0.0% | 0 | 305.02s | 106 | 127,006 | 127,125 | |
| Hy4 preview | 3.0 | 10.0 | 0.0% | 0 | 597.45s | 246 | 6 | 128,230 |
Quick Compare
Switch Comparison Pair
Hy4 previewlowvsMiMo-V2.6-FlashnoneStep 3.5 FlashmediumvsHy4 previewlowNorth Mini CodemediumFree AvailablevsQwen3.8 27BnoneFree AvailableNorth Mini CodemediumFree AvailablevsMiMo-V2.6-FlashnoneEmber-1nonevsHy4 previewlowQwen3.8 27BnoneFree AvailablevsHy4 previewlowNorth Mini CodemediumFree AvailablevsEmber-1noneSeed-2.0-CodenonevsNorth Mini CodemediumFree AvailableSeed-2.0-CodenonevsHy4 previewlowGPT-5.6 LunanonevsHy4 previewlowNorth Mini CodemediumFree AvailablevsGPT-5.6 LunanoneNorth Mini CodemediumFree AvailablevsGemma 4 26B A4BnoneFree Available