- Rank
- #86
- Total Output Tokens
- 253,807
- Response Time (avg)
- 73.02s
- Total Cost
- $0.881
Seed-2.0-Code (low) vs Qwen3.7 Plus (medium)
Qwen3.7 Plus (medium) leads on average score with 8.3 vs 8.1. Qwen3.7 Plus (medium) has the lower benchmark cost at $0.432 vs $0.881. Qwen3.7 Plus (medium) is faster at 59.73s vs 73.02s, with pass rates of 78.3% vs 76.8%.
Compared models
- Rank
- #81
- Total Output Tokens
- 215,560
- Response Time (avg)
- 59.73s
- Total Cost
- $0.432
Recommended model
Qwen3.7 Plus (medium)
It has the best score here (8.3), while costing about 2.0x less than Seed-2.0-Code (low).
Detailed comparison
| Metric | Seed-2.0-Code Seed-2.0-Code low | Qwen3.7 Plus Qwen3.7 Plus medium |
|---|---|---|
| Score | 8.1 | 8.3 |
| Rank | #86 | #81 |
| Reliability | 8.9 | 10.0 |
| Consistency | 7.9 | 8.9 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 78.3% | 76.8% |
| Flaky tests | 6 | 3 |
| Total Runs | 69 | 69 |
| Cost per result | 6.288 | 2.697 |
| Total Cost | $0.881 | $0.432 |
| Input Price | $0.500 / 1M | $0.320 / 1M |
| Output Price | $3.000 / 1M | $1.280 / 1M |
| Total Input Tokens | 237,604 | 350,546 |
| Output Tokens | 9,617 | 8,576 |
| Reasoning Tokens | 244,190 | 206,984 |
| Response Time (avg) | 73.02s | 59.73s |
| Response Time (max) | 485.92s | 315.30s |
| Response Time (total) | 1679.49s | 1373.73s |
| Parameters | ~200B total (~20B active) | ~397B total (~17B active) |
| Availability | Closed | Closed |
Model generation showcase
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#86 Seed-2.0-Code
low
Provider returned error
- Cost
- $0.000
- Time
- 0.3s
- Tokens
- 0 tok
#81 Qwen3.7 Plus
medium- Cost
- $0.018
- Time
- 193.2s
- Tokens
- 10,821 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 |
|---|---|---|---|---|---|---|---|---|---|
| Seed-2.0-Code | 10.0 | 10.0 | 100.0% | 0 | 90.18s | 151,947 | 1,475 | 11,023 | |
| Qwen3.7 Plus | 10.0 | 10.0 | 100.0% | 0 | 196.47s | 235,304 | 2,413 | 25,810 |
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Seed-2.0-Code | 8.7 | 7.9 | 91.7% | 1 | 39.56s | 930 | 2,650 | 15,987 | |
| Qwen3.7 Plus | 10.0 | 10.0 | 100.0% | 0 | 8.58s | 672 | 195 | 5,065 |
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Seed-2.0-Code | 7.0 | 7.1 | 55.6% | 1 | 109.70s | 7,948 | 455 | 55,759 | |
| Qwen3.7 Plus | 6.1 | 6.6 | 55.6% | 1 | 108.60s | 6,472 | 414 | 43,576 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Seed-2.0-Code | 7.3 | 5.8 | 83.3% | 1 | 99.12s | 55,969 | 3,774 | 21,408 | |
| Qwen3.7 Plus | 8.2 | 6.9 | 66.7% | 1 | 190.27s | 89,228 | 4,403 | 57,645 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Seed-2.0-Code | 10.0 | 10.0 | 100.0% | 0 | 24.88s | 8,046 | 246 | 1,639 | |
| Qwen3.7 Plus | 10.0 | 10.0 | 100.0% | 0 | 21.75s | 7,782 | 270 | 6,713 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Seed-2.0-Code | 4.1 | 4.4 | 44.5% | 2 | 238.45s | 975 | 16 | 132,626 | |
| Qwen3.7 Plus | 3.6 | 7.2 | 22.2% | 1 | 60.05s | 780 | 58 | 34,980 |
| General Intelligence | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Seed-2.0-Code | 6.5 | 3.4 | 66.7% | 1 | 11.14s | 579 | 179 | 1,117 | |
| Qwen3.7 Plus | 10.0 | 10.0 | 100.0% | 0 | 25.48s | 516 | 123 | 3,998 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Seed-2.0-Code | 9.8 | 10.0 | 100.0% | 0 | 12.20s | 828 | 72 | 1,034 | |
| Qwen3.7 Plus | 10.0 | 10.0 | 100.0% | 0 | 16.13s | 699 | 102 | 5,013 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Seed-2.0-Code | 9.9 | 10.0 | 100.0% | 0 | 12.50s | 885 | 445 | 2,470 | |
| Qwen3.7 Plus | 10.0 | 10.0 | 100.0% | 0 | 16.38s | 696 | 280 | 7,312 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Seed-2.0-Code | 10.0 | 10.0 | 100.0% | 0 | 55.56s | 9,315 | 296 | 637 | |
| Qwen3.7 Plus | 10.0 | 10.0 | 100.0% | 0 | 15.02s | 8,193 | 292 | 1,831 |
| Trivia | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Seed-2.0-Code | 3.0 | 10.0 | 0.0% | 0 | 10.02s | 182 | 9 | 490 | |
| Qwen3.7 Plus | 3.0 | 10.0 | 0.0% | 0 | 91.07s | 204 | 26 | 15,041 |
Quick Compare
Switch Comparison Pair
Qwen3.7 PlusmediumvsGrok 4.5highKimi K3maxvsQwen3.7 PlusmediumSeed-2.0-CodelowvsDeepSeek V4 Pro 0423highGemini 3.5 FlashhighvsQwen3.7 PlusmediumClaude Opus 4.7mediumvsSeed-2.0-CodelowSeed-2.0-CodelowvsDeepSeek V4 Flash 0423highGPT-5.6 TerrahighvsQwen3.7 PlusmediumSeed-2.0-CodelowvsGPT-5.6 TerramediumSeed-2.0-CodelowvsGLM 5.2mediumQwen3.7 PlusmediumvsGLM 5.2highSeed-2.0-CodelowvsGrok 4.5highDeepSeek V4 Flash 0731highvsQwen3.7 Plusmedium