AI BENCHY Compare
OpenAI: GPT-5.3-Codex vs OpenAI: GPT-5.4
Compare:
Last updated at: 2026-03-05
| Metric | OpenAI: GPT-5.3-Codex medium Release: 2026-02-05 | OpenAI: GPT-5.4 medium Release: 2026-03-05 |
|---|---|---|
| Avg Score | 8.7 | 8.2 |
| Tests Correct | ||
| Rank | #4 | #7 |
| Consistency | 9.0 | 8.9 |
| Cost per result | 4.418 | 6.533 |
| Total Cost | $0.531 | $0.784 |
| Attempt pass rate | 88.9% | 86.7% |
| Flaky tests | 2 | 2 |
| common.totalAttempts | 45 (15 x 3) | 45 (15 x 3) |
| Output Tokens | 1,577 | 1,611 |
| Reasoning Tokens | 33,017 | 46,321 |
| Response Time (avg) | 17.37s | 21.06s |
| Response Time (max) | 100.93s | 100.41s |
| Response Time (total) | 260.52s | 315.95s |
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-5.3-Codex | 10.0 | 10.0 | 100.0% | 0 | 4.69s | 216 | 1,421 | |
| OpenAI: GPT-5.4 | 10.0 | 10.0 | 100.0% | 0 | 5.02s | 216 | 1,466 |
| Combined | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.3-Codex | 10.0 | 10.0 | 100.0% | 0 | 19.56s | 364 | 2,731 | |
| OpenAI: GPT-5.4 | 10.0 | 10.0 | 100.0% | 0 | 20.57s | 301 | 3,543 |
| Data parsing and extraction | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.3-Codex | 9.9 | 10.0 | 100.0% | 0 | 3.07s | 234 | 728 | |
| OpenAI: GPT-5.4 | 9.9 | 10.0 | 100.0% | 0 | 5.32s | 234 | 804 |
| Domain specific | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.3-Codex | 4.0 | 7.2 | 55.6% | 1 | 64.31s | 64 | 25,308 | |
| OpenAI: GPT-5.4 | 4.0 | 7.2 | 44.4% | 1 | 74.27s | 61 | 34,748 |
| Instructions following | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.3-Codex | 10.0 | 10.0 | 100.0% | 0 | 3.04s | 93 | 693 | |
| OpenAI: GPT-5.4 | 10.0 | 10.0 | 100.0% | 0 | 3.11s | 93 | 897 |
| Puzzle Solving | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.3-Codex | 9.3 | 7.9 | 88.9% | 1 | 5.12s | 352 | 1,644 | |
| OpenAI: GPT-5.4 | 7.0 | 7.2 | 88.9% | 1 | 9.13s | 442 | 3,832 |
| Tool Calling | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.3-Codex | 10.0 | 10.0 | 100.0% | 0 | 6.37s | 254 | 492 | |
| OpenAI: GPT-5.4 | 10.0 | 10.0 | 100.0% | 0 | 13.28s | 264 | 1,031 |
Quick Compare
Switch Comparison Pair
Gemini 3 Flash PreviewlowvsGPT-5.4mediumGemini 3.1 Flash Lite PreviewhighvsGPT-5.4mediumGemini 3 Flash PreviewlowvsGPT-5.3-CodexmediumGemini 3.1 Flash Lite PreviewlowvsGPT-5.4mediumGemini 3.1 Flash Lite PreviewhighvsGPT-5.3-CodexmediumGemini 3.1 Flash Lite PreviewnonevsGPT-5.4mediumGemini 3.1 Flash Lite PreviewlowvsGPT-5.3-CodexmediumGemini 3 Flash PreviewnonevsGPT-5.4mediumGemini 3.1 Flash Lite PreviewnonevsGPT-5.3-CodexmediumClaude Sonnet 4.6nonevsGPT-5.4mediumGemini 3 Flash PreviewnonevsGPT-5.3-CodexmediumGPT-5.4mediumvsQwen3.5 Plus 2026-02-15none