- Rank
- #89
- Total Output Tokens
- 80,538
- Response Time (avg)
- 31.29s
- Total Cost
- $1.558
GPT-5.2 (medium) vs Qwen4 Max (low)
The average score is effectively tied at 8.7 vs 8.7. Qwen4 Max (low) has the lower benchmark cost at $1.064 vs $1.558. GPT-5.2 (medium) is faster at 31.29s vs 56.68s, with pass rates of 73.9% vs 87.0%.
Compared models
- Rank
- #94
- Total Output Tokens
- 144,069
- Response Time (avg)
- 56.68s
- Total Cost
- $1.064
Recommended model
GPT-5.2 (medium)
It has the best score here (8.7), while responding about 1.8x faster than Qwen4 Max (low).
Detailed comparison
| Metric | GPT-5.2 GPT-5.2 medium | Qwen4 Max Qwen4 Max low |
|---|---|---|
| Score | 8.7 | 8.7 |
| Rank | #89 | #94 |
| Reliability | 10.0 | 9.9 |
| Consistency | 8.5 | 10.0 |
| Attempts | 69/69 | 69/69 |
| Tests Correct | ||
| Attempt pass rate | 73.9% | 87.0% |
| Flaky tests | 4 | 0 |
| Total Runs | 69 | 69 |
| Cost per result | 10.261 | 5.318 |
| Total Cost | $1.558 | $1.064 |
| Input Price | $1.750 / 1M | $1.500 / 1M |
| Output Price | $14.000 / 1M | $4.500 / 1M |
| Cache Read Price | $0.175 / 1M | $0.075 / 1M |
| Cache Write Price | N/A | $1.875 / 1M |
| Total Input Tokens | 235,207 | 276,790 |
| Output Tokens | 11,065 | 8,266 |
| Reasoning Tokens | 69,473 | 135,803 |
| Response Time (avg) | 31.29s | 56.68s |
| Response Time (max) | 116.86s | 564.77s |
| Response Time (total) | 531.98s | 1303.63s |
| Parameters | ~1.2T total (~80B active) | ~2.4T total (~95B active) |
| Availability | Closed | 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.
#89 GPT-5.2
medium- Cost
- $0.047
- Time
- 49.2s
- Tokens
- 3,396 tok
#94 Qwen4 Max
low- Cost
- $0.064
- Time
- 239.1s
- Tokens
- 14,300 tok
Category Breakdown
Quick Compare
Switch Comparison Pair
Claude Fable 5.2highvsQwen4 MaxlowGPT-5.2mediumvsQwen3.8 27BhighFree AvailableSeed 2.1 TurbomediumvsQwen4 MaxlowQwen4 MaxlowvsMiMo-V2.6-PromediumGPT-5.2mediumvsParticle-1xhighMuse EmbermaxvsQwen4 MaxlowClaude Fable 5.2highvsGPT-5.2mediumERNIE-Light-DT-1.0highvsQwen4 MaxlowDeepSeek V4.1 FlashmaxvsQwen4 MaxlowParticle-1xhighvsQwen4 MaxlowMuse EmberlowvsGPT-5.2mediumMuse EmbermaxvsGPT-5.2medium