Model comparison
GPT-5.4 Pro vs gpt-oss-20b
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 32.5 on the Noometry Index. gpt-oss-20b costs 1875× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
Summary
- They share 5 benchmarks with published results for both. GPT-5.4 Pro scores higher in 4 categories and gpt-oss-20b in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 Pro leads 70.7 to 19.3.
- The biggest single-benchmark swing is Chess Puzzles: 58.6% for GPT-5.4 Pro and 4% for gpt-oss-20b.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.
- GPT-5.4 Pro accepts more context: 1.05M tokens versus 131K.
- gpt-oss-20b has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 Pro | gpt-oss-20b | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 58.9 | 32.5 |
| Released | 2026-03-05 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 128K | 16K |
| Input $ / M tokens | $30 | $0.018 |
| Output $ / M tokens | $180 | $0.09 |
| Results tracked | 16 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 Pro leads
GPT-5.4 Pro: 43.2 (#90), gpt-oss-20b: 37.6 (#192)
| Benchmark | GPT-5.4 Pro | gpt-oss-20b |
|---|---|---|
| WeirdML | 57.4% | 40.9% |
| SciCode | — | 34.4% |
| LMArena Coding | — | 1306 |
| ALE-Bench | — | 566.05 |
Agentic & Tool Use Not comparable
GPT-5.4 Pro: —, gpt-oss-20b: 9.3 (#154)
| Benchmark | GPT-5.4 Pro | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
Reasoning GPT-5.4 Pro leads
GPT-5.4 Pro: 70.7 (#13), gpt-oss-20b: 19.3 (#261)
| Benchmark | GPT-5.4 Pro | gpt-oss-20b |
|---|---|---|
| CritPt | 30% | 1.4% |
| Chess Puzzles | 58.6% | 4% |
| Epoch Capabilities Index | 158.93 | 137.82 |
| ARC-AGI-2 | 83.3% | — |
| SimpleBench | 74.1% | — |
| Kagi LLM Benchmark | — | 53.2% |
| ARC-AGI-1 | 94.5% | — |
| EnigmaEval | 23.8% | — |
| LMArena Hard Prompts | — | 1274 |
| DTBench | — | 68% |
| LMCA | — | 14.5% |
Math GPT-5.4 Pro leads
GPT-5.4 Pro: 72.4 (#22), gpt-oss-20b: 39.4 (#103)
| Benchmark | GPT-5.4 Pro | gpt-oss-20b |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | — |
| FrontierMath Tier 4 | 58.5% | — |
| OTIS Mock AIME 2024-2025 | — | 65.3% |
| Omni-MATH | — | 56.5% |
| LMArena Math | — | 1317 |
| FrontierMath (Feb 2025 set) | 50% | — |
| FrontierMath Tier 4 (v1) | 37.5% | — |
Knowledge GPT-5.4 Pro leads
GPT-5.4 Pro: 68.3 (#7), gpt-oss-20b: 34.6 (#195)
| Benchmark | GPT-5.4 Pro | gpt-oss-20b |
|---|---|---|
| GPQA Diamond | 94.6% | 60.8% |
| Humanity's Last Exam | 44.3% | — |
| SimpleQA Verified | 46.3% | — |
| MMLU-Pro | — | 74% |
| Vectara Hallucination Rate | 8.3% | — |
| GPQA (HELM) | — | 59.4% |
| LMArena Expert | — | 1258 |
Multilingual Not comparable
GPT-5.4 Pro: —, gpt-oss-20b: 42.2 (#197)
| Benchmark | GPT-5.4 Pro | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | — | 1268 |
| LMArena Chinese | — | 1314 |
| LMArena German | — | 1255 |
| LMArena Japanese | — | 1244 |
| LMArena Korean | — | 1236 |
| LMArena Russian | — | 1278 |
| LMArena Spanish | — | 1267 |
Instruction Following Not comparable
GPT-5.4 Pro: —, gpt-oss-20b: 61.8 (#240)
| Benchmark | GPT-5.4 Pro | gpt-oss-20b |
|---|---|---|
| IFEval | — | 73.2% |
| LMArena Instruction Following | — | 1236 |
Long Context Not comparable
GPT-5.4 Pro: —, gpt-oss-20b: 37.9 (#209)
| Benchmark | GPT-5.4 Pro | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | — | 1250 |
Writing & Preference Not comparable
GPT-5.4 Pro: —, gpt-oss-20b: 35.5 (#265)
| Benchmark | GPT-5.4 Pro | gpt-oss-20b |
|---|---|---|
| LMArena Text | — | 1287 |
| LMArena Creative Writing | — | 1201 |
| EQ-Bench Creative Writing | — | 666 |
| WildBench | — | 73.7% |
| LMArena Multi-Turn | — | 1268 |
Frequently asked questions
Is GPT-5.4 Pro better than gpt-oss-20b?
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 32.5 on the Noometry Index. gpt-oss-20b costs 1875× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5.4 Pro or gpt-oss-20b?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; GPT-5.4 Pro lists at $30 and $180.
Is GPT-5.4 Pro or gpt-oss-20b better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 43.2 versus 37.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 Pro does, with 1.05M tokens against 131K.
How many benchmarks do GPT-5.4 Pro and gpt-oss-20b share?
5 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and gpt-oss-20b has 34.