AI BENCHY Compare
OpenAI: GPT-5.4 vs Qwen: Qwen3.5-35B-A3B
Compare:
Last updated at: 2026-03-05
| Metric | OpenAI: GPT-5.4 none Release: 2026-03-05 | Qwen: Qwen3.5-35B-A3B none Release: 2026-02-24 |
|---|---|---|
| Avg Score | 4.6 | 4.7 |
| Tests Correct | ||
| Rank | #44 | #43 |
| Consistency | 8.9 | 8.9 |
| Cost per result | 1.496 | 0.233 |
| Total Cost | $0.090 | $0.014 |
| Attempt pass rate | 44.4% | 48.9% |
| Flaky tests | 2 | 2 |
| common.totalAttempts | 45 (15 x 3) | 45 (15 x 3) |
| Output Tokens | 1,635 | 3,642 |
| Reasoning Tokens | 0 | 0 |
| Response Time (avg) | 1.46s | 4.30s |
| Response Time (max) | 2.89s | 47.43s |
| Response Time (total) | 21.86s | 64.43s |
Score vs Total Cost
Response Time (avg)
Avg Score vs Response Time (avg)
Category Breakdown
| Anti-AI Tricks | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.4 | 10.0 | 7.3 | 11.1% | 1 | 1.41s | 388 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 10.0 | 7.2 | 22.2% | 1 | 1.76s | 569 | 0 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.4 | 10.0 | 10.0 | 0.0% | 0 | 2.89s | 291 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 10.0 | 10.0 | 0.0% | 0 | 47.43s | 1,833 | 0 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.4 | 9.9 | 10.0 | 100.0% | 0 | 1.04s | 222 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 9.9 | 10.0 | 100.0% | 0 | 1.16s | 243 | 0 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.4 | 4.0 | 7.2 | 44.4% | 1 | 1.07s | 50 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 7.0 | 10.0 | 66.7% | 0 | 485ms | 15 | 0 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.4 | 5.5 | 10.0 | 50.0% | 0 | 1.07s | 81 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 5.0 | 10.0 | 50.0% | 0 | 809ms | 63 | 0 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.4 | 4.0 | 9.8 | 33.3% | 0 | 1.52s | 357 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 1.7 | 7.4 | 22.2% | 1 | 1.34s | 655 | 0 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.4 | 10.0 | 10.0 | 100.0% | 0 | 2.75s | 246 | 0 | |
| Qwen: Qwen3.5-35B-A3B | 10.0 | 10.0 | 100.0% | 0 | 2.30s | 264 | 0 |
Quick Compare
Switch Comparison Pair
MiniMax M2.5mediumvsQwen3.5-35B-A3BnoneMiniMax M2.5mediumvsGPT-5.4nonegpt-oss-120bmediumFree AvailablevsQwen3.5-35B-A3BnoneMercury 2mediumvsQwen3.5-35B-A3BnoneMercury 2mediumvsGPT-5.4noneGPT-5 NanomediumvsQwen3.5-35B-A3BnoneGPT-5.4nonevsQwen3.5-35B-A3BmediumGPT-5.4nonevsQwen3 Coder NextmediumGPT-5.4nonevsGLM 4.7 FlashmediumGPT-5 MinimediumvsQwen3.5-35B-A3BnoneQwen3.5-35B-A3BnonevsGLM 4.7 FlashmediumClaude Opus 4.6mediumvsQwen3.5-35B-A3Bnone