AI BENCHY Compare
OpenAI: GPT-5 Mini vs Qwen: Qwen3.5-35B-A3B
Compare:
Last updated at: 2026-03-03
| Metric | OpenAI: GPT-5 Mini medium Release: 2025-08-07 | Qwen: Qwen3.5-35B-A3B medium Release: 2026-02-24 |
|---|---|---|
| Rank | #33 | #30 |
| Avg Score | 5.77 | 5.93 |
| Consistency | 8.79 | 6.62 |
| Cost per result | 1.200 | 5.169 |
| Total Cost | $0.084 | $0.362 |
| Tests Correct | ||
| Attempt pass rate | 57.1% | 73.8% |
| Flaky tests | 2 | 6 |
| Output Tokens | 4,723 | 1,317 |
| Reasoning Tokens | 35,392 | 177,502 |
Score vs Total Cost
Category Breakdown
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5 Mini | 7.00 | 9.62 | 66.7% | 0 | 1,645 | 5,824 | |
| Qwen: Qwen3.5-35B-A3B | 10.00 | 10.00 | 100.0% | 0 | 429 | 36,235 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5 Mini | 9.88 | 10.00 | 100.0% | 0 | 453 | 3,200 | |
| Qwen: Qwen3.5-35B-A3B | 5.50 | 5.87 | 83.3% | 1 | 235 | 19,493 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5 Mini | 1.00 | 7.21 | 22.2% | 1 | 293 | 14,016 | |
| Qwen: Qwen3.5-35B-A3B | 1.00 | 4.41 | 44.5% | 2 | 41 | 46,368 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5 Mini | 7.00 | 6.64 | 66.7% | 1 | 318 | 4,992 | |
| Qwen: Qwen3.5-35B-A3B | 8.00 | 6.80 | 66.7% | 1 | 97 | 17,361 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5 Mini | 4.33 | 9.78 | 33.3% | 0 | 1,527 | 5,760 | |
| Qwen: Qwen3.5-35B-A3B | 4.33 | 4.70 | 66.7% | 2 | 206 | 56,680 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5 Mini | 10.00 | 10.00 | 100.0% | 0 | 487 | 1,600 | |
| Qwen: Qwen3.5-35B-A3B | 10.00 | 10.00 | 100.0% | 0 | 309 | 1,365 |
Quick Compare
Switch Comparison Pair
Qwen3.5-35B-A3BmediumvsGLM 5noneGPT-5 MinimediumvsGLM 5noneClaude Sonnet 4.6nonevsQwen3.5-35B-A3BmediumGemini 2.5 FlashnonevsGPT-5 MinimediumGPT-5 MinimediumvsQwen3.5 Plus 2026-02-15noneGPT-5 MinimediumvsQwen3.5-122B-A10BnoneClaude Sonnet 4.6nonevsGPT-5 MinimediumGemini 2.5 FlashnonevsQwen3.5-35B-A3BmediumDeepSeek V3.2nonevsGPT-5 MinimediumGPT-5 MinimediumvsQwen3.5-27BnoneGPT-4o-mininonevsQwen3.5-35B-A3BmediumGPT-5 MinimediumvsQwen3.5-35B-A3Bnone