Model comparison
GPT-5.4 mini vs GPT-5-Codex
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 37.9 on the Noometry Index.
Last verified . 2 shared benchmarks.
Summary
- They share 2 benchmarks with published results for both. GPT-5.4 mini scores higher in 1 category and GPT-5-Codex in 2 categories; 2 gaps are clear of the uncertainty.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.9% for GPT-5.4 mini and 70.3% for GPT-5-Codex.
- GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
Side by side
| GPT-5.4 mini | GPT-5-Codex | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 45.0 | 37.9 |
| Released | 2026-03-17 | 2025-09-15 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $0.75 | $1.25 |
| Output $ / M tokens | $4.50 | $10 |
| Results tracked | 46 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
GPT-5.4 mini: 45.2 (#72), GPT-5-Codex: 42.4 (#103)
| Benchmark | GPT-5.4 mini | GPT-5-Codex |
|---|---|---|
| WeirdML | 60.3% | 54.5% |
| FrontierCode | 27% | — |
| LMArena WebDev | 1397 | — |
| SciCode | 49.9% | — |
| LMArena Coding | 1438 | — |
| ALE-Bench | 1,189 | — |
Agentic & Tool Use GPT-5-Codex leads
GPT-5.4 mini: 29.9 (#81), GPT-5-Codex: 31.0 (#72)
| Benchmark | GPT-5.4 mini | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | — | 44.3% |
| DeepResearch Bench | 36.3% | — |
Reasoning Too close to call
GPT-5.4 mini: 30.4 (#85), GPT-5-Codex: 30.9 (#83)
| Benchmark | GPT-5.4 mini | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | 37.9% | 70.3% |
| ARC-AGI-2 | 18.9% | — |
| NYT Connections (extended) | 61.8% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| LMArena Hard Prompts | 1424 | — |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LMCA | 40.8% | — |
| Epoch Capabilities Index | 148.84 | — |
| ForecastBench | 57 | — |
Math Not comparable
GPT-5.4 mini: 45.5 (#75), GPT-5-Codex: —
| Benchmark | GPT-5.4 mini | GPT-5-Codex |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 21% | — |
| LMArena Math | 1419 | — |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Not comparable
GPT-5.4 mini: 51.5 (#67), GPT-5-Codex: —
| Benchmark | GPT-5.4 mini | GPT-5-Codex |
|---|---|---|
| GPQA Diamond | 86.9% | — |
| SimpleQA Verified | 29.4% | — |
| Vectara Hallucination Rate | 5.5% | — |
| LMArena Expert | 1435 | — |
Multimodal Not comparable
GPT-5.4 mini: 39.7 (#56), GPT-5-Codex: —
| Benchmark | GPT-5.4 mini | GPT-5-Codex |
|---|---|---|
| LMArena Vision | 1245 | — |
Multilingual Not comparable
GPT-5.4 mini: 51.9 (#96), GPT-5-Codex: —
| Benchmark | GPT-5.4 mini | GPT-5-Codex |
|---|---|---|
| LMArena Non-English | 1405 | — |
| LMArena Chinese | 1446 | — |
| LMArena French | 1440 | — |
| LMArena German | 1409 | — |
| LMArena Japanese | 1374 | — |
| LMArena Korean | 1368 | — |
| LMArena Russian | 1417 | — |
| LMArena Spanish | 1405 | — |
Instruction Following Not comparable
GPT-5.4 mini: 74.1 (#102), GPT-5-Codex: —
| Benchmark | GPT-5.4 mini | GPT-5-Codex |
|---|---|---|
| LMArena Instruction Following | 1405 | — |
Long Context Not comparable
GPT-5.4 mini: 43.0 (#112), GPT-5-Codex: —
| Benchmark | GPT-5.4 mini | GPT-5-Codex |
|---|---|---|
| LMArena Longer Query | 1407 | — |
Writing & Preference Not comparable
GPT-5.4 mini: 64.0 (#58), GPT-5-Codex: —
| Benchmark | GPT-5.4 mini | GPT-5-Codex |
|---|---|---|
| LMArena Text | 1412 | — |
| LMArena Creative Writing | 1370 | — |
| EQ-Bench Creative Writing | 1665 | — |
| LMArena Multi-Turn | 1429 | — |
Frequently asked questions
Is GPT-5.4 mini better than GPT-5-Codex?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 37.9 on the Noometry Index.
Which is cheaper, GPT-5.4 mini or GPT-5-Codex?
GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; GPT-5-Codex lists at $1.25 and $10.
Is GPT-5.4 mini or GPT-5-Codex better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Both accept 400K tokens.
How many benchmarks do GPT-5.4 mini and GPT-5-Codex share?
2 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and GPT-5-Codex has 3.