AI BENCHY Compare
OpenAI: GPT-5.4 vs Qwen: Qwen3.5-27B
Compare:
Last updated at: 2026-03-05
| Metric | OpenAI: GPT-5.4 medium Release: 2026-03-05 | Qwen: Qwen3.5-27B medium Release: 2026-02-24 |
|---|---|---|
| Avg Score | 8.2 | 8.5 |
| Tests Correct | ||
| Rank | #7 | #5 |
| Consistency | 8.9 | 9.5 |
| Cost per result | 6.533 | 3.283 |
| Total Cost | $0.784 | $0.394 |
| Attempt pass rate | 86.7% | 82.2% |
| Flaky tests | 2 | 1 |
| common.totalAttempts | 45 (15 x 3) | 45 (15 x 3) |
| Output Tokens | 1,611 | 1,588 |
| Reasoning Tokens | 46,321 | 177,639 |
| Response Time (avg) | 21.06s | 48.85s |
| Response Time (max) | 100.41s | 163.96s |
| Response Time (total) | 315.95s | 732.75s |
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 | 10.0 | 100.0% | 0 | 5.02s | 216 | 1,466 | |
| Qwen: Qwen3.5-27B | 10.0 | 10.0 | 100.0% | 0 | 9.69s | 102 | 8,956 |
| 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 | 100.0% | 0 | 20.57s | 301 | 3,543 | |
| Qwen: Qwen3.5-27B | 10.0 | 10.0 | 100.0% | 0 | 163.96s | 483 | 9,991 |
| 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 | 5.32s | 234 | 804 | |
| Qwen: Qwen3.5-27B | 9.9 | 10.0 | 100.0% | 0 | 30.26s | 270 | 16,150 |
| 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 | 74.27s | 61 | 34,748 | |
| Qwen: Qwen3.5-27B | 4.0 | 10.0 | 33.3% | 0 | 79.53s | 43 | 52,368 |
| Instructions following | 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 | 3.11s | 93 | 897 | |
| Qwen: Qwen3.5-27B | 10.0 | 10.0 | 100.0% | 0 | 19.66s | 97 | 11,638 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.4 | 7.0 | 7.2 | 88.9% | 1 | 9.13s | 442 | 3,832 | |
| Qwen: Qwen3.5-27B | 8.3 | 7.7 | 77.8% | 1 | 64.61s | 245 | 77,213 |
| 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 | 13.28s | 264 | 1,031 | |
| Qwen: Qwen3.5-27B | 10.0 | 10.0 | 100.0% | 0 | 7.45s | 348 | 1,323 |
Quick Compare
Switch Comparison Pair
Gemini 3 Flash PreviewlowvsGPT-5.4mediumGemini 3.1 Flash Lite PreviewhighvsGPT-5.4mediumGemini 3 Flash PreviewlowvsQwen3.5-27BmediumGemini 3.1 Flash Lite PreviewhighvsQwen3.5-27BmediumGemini 3.1 Flash Lite PreviewlowvsGPT-5.4mediumGemini 3.1 Flash Lite PreviewnonevsGPT-5.4mediumGPT-5.2 ChatnonevsQwen3.5-27BmediumGemini 3.1 Flash Lite PreviewlowvsQwen3.5-27BmediumGPT-5.3 ChatnonevsQwen3.5-27BmediumGemini 3.1 Flash Lite PreviewnonevsQwen3.5-27BmediumGemini 3 Flash PreviewnonevsGPT-5.4mediumClaude Sonnet 4.6nonevsGPT-5.4medium