Model comparison
Chatgpt 4o Latest 20250326 vs gpt-oss-20b
Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.8 to 32.5 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Chatgpt 4o Latest 20250326 scores higher in 7 categories and gpt-oss-20b in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Chatgpt 4o Latest 20250326 leads 62.6 to 35.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 75% for Chatgpt 4o Latest 20250326 and 53.2% for gpt-oss-20b.
- gpt-oss-20b has downloadable open weights; the other is API-only.
Side by side
| Chatgpt 4o Latest 20250326 | gpt-oss-20b | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 43.8 | 32.5 |
| Released | — | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.018 |
| Output $ / M tokens | — | $0.09 |
| Results tracked | 21 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 41.6 (#122), gpt-oss-20b: 37.6 (#192)
| Benchmark | Chatgpt 4o Latest 20250326 | gpt-oss-20b |
|---|---|---|
| LMArena Coding | 1413 | 1306 |
| SciCode | — | 34.4% |
| WeirdML | — | 40.9% |
| ALE-Bench | — | 566.05 |
Agentic & Tool Use Not comparable
Chatgpt 4o Latest 20250326: —, gpt-oss-20b: 9.3 (#154)
| Benchmark | Chatgpt 4o Latest 20250326 | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
Reasoning Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 33.8 (#71), gpt-oss-20b: 19.3 (#261)
| Benchmark | Chatgpt 4o Latest 20250326 | gpt-oss-20b |
|---|---|---|
| Kagi LLM Benchmark | 75% | 53.2% |
| LMArena Hard Prompts | 1424 | 1274 |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 4% |
| DTBench | — | 68% |
| LMCA | — | 14.5% |
| Epoch Capabilities Index | — | 137.82 |
Math Too close to call
Chatgpt 4o Latest 20250326: 38.6 (#134), gpt-oss-20b: 39.4 (#103)
| Benchmark | Chatgpt 4o Latest 20250326 | gpt-oss-20b |
|---|---|---|
| LMArena Math | 1407 | 1317 |
| OTIS Mock AIME 2024-2025 | — | 65.3% |
| Omni-MATH | — | 56.5% |
Knowledge Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 39.2 (#137), gpt-oss-20b: 34.6 (#195)
| Benchmark | Chatgpt 4o Latest 20250326 | gpt-oss-20b |
|---|---|---|
| LMArena Expert | 1401 | 1258 |
| GPQA Diamond | — | 60.8% |
| MMLU-Pro | — | 74% |
| Confabulations | 16.6% | — |
| GPQA (HELM) | — | 59.4% |
Multimodal Not comparable
Chatgpt 4o Latest 20250326: 39.6 (#58), gpt-oss-20b: —
| Benchmark | Chatgpt 4o Latest 20250326 | gpt-oss-20b |
|---|---|---|
| LMArena Vision | 1243 | — |
Multilingual Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 52.9 (#76), gpt-oss-20b: 42.2 (#197)
| Benchmark | Chatgpt 4o Latest 20250326 | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1419 | 1268 |
| LMArena Chinese | 1457 | 1314 |
| LMArena German | 1423 | 1255 |
| LMArena Japanese | 1405 | 1244 |
| LMArena Korean | 1396 | 1236 |
| LMArena Russian | 1429 | 1278 |
| LMArena Spanish | 1434 | 1267 |
| LMArena French | 1446 | — |
Instruction Following Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 74.0 (#107), gpt-oss-20b: 61.8 (#240)
| Benchmark | Chatgpt 4o Latest 20250326 | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1403 | 1236 |
| IFEval | — | 73.2% |
Long Context Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 43.1 (#107), gpt-oss-20b: 37.9 (#209)
| Benchmark | Chatgpt 4o Latest 20250326 | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1413 | 1250 |
Writing & Preference Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 62.6 (#72), gpt-oss-20b: 35.5 (#265)
| Benchmark | Chatgpt 4o Latest 20250326 | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1429 | 1287 |
| LMArena Creative Writing | 1405 | 1201 |
| EQ-Bench Creative Writing | 1501 | 666 |
| LMArena Multi-Turn | 1454 | 1268 |
| WildBench | — | 73.7% |
Frequently asked questions
Is Chatgpt 4o Latest 20250326 better than gpt-oss-20b?
Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.8 to 32.5 on the Noometry Index.
Is Chatgpt 4o Latest 20250326 or gpt-oss-20b better for coding?
Chatgpt 4o Latest 20250326 scores higher on coding benchmarks: 41.6 versus 37.6 in the Noometry coding category.
How many benchmarks do Chatgpt 4o Latest 20250326 and gpt-oss-20b share?
18 benchmarks have published results for both models. Chatgpt 4o Latest 20250326 has 21 scored results on Noometry and gpt-oss-20b has 34.