Model comparison
Chatgpt 4o Latest 20250326 vs DeepSeek-V3.1
Chatgpt 4o Latest 20250326 and DeepSeek-V3.1 score almost the same on the Noometry Index (43.2 vs 42.2), so choose on price, context window or the category you care about most.
Last verified . 19 shared benchmarks.
DeepSeekSummary
- They share 19 benchmarks with published results for both. Chatgpt 4o Latest 20250326 scores higher in 6 categories and DeepSeek-V3.1 in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in long context, where Chatgpt 4o Latest 20250326 leads 43.1 to 36.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 75% for Chatgpt 4o Latest 20250326 and 53.2% for DeepSeek-V3.1.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| Chatgpt 4o Latest 20250326 | DeepSeek-V3.1 | |
|---|---|---|
| Provider | OpenAI | DeepSeek |
| Noometry Index | 43.2 | 42.2 |
| Released | — | 2025-08-21 |
| Weights | Proprietary | Open |
| Context window | — | 164K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.95 |
| Results tracked | 21 | 27 |
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: 41.0 (#122), DeepSeek-V3.1: 39.8 (#140)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Coding | 1413 | 1417 |
| WeirdML | — | 38.4% |
Reasoning Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 32.8 (#64), DeepSeek-V3.1: 27.3 (#109)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-V3.1 |
|---|---|---|
| Kagi LLM Benchmark | 75% | 53.2% |
| LMArena Hard Prompts | 1424 | 1417 |
| SimpleBench | — | 40% |
| DTBench | — | 82.7% |
| LMCA | — | 24.3% |
| Epoch Capabilities Index | — | 139.92 |
| ForecastBench | — | 58 |
Math Too close to call
Chatgpt 4o Latest 20250326: 35.8 (#134), DeepSeek-V3.1: 36.1 (#125)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Math | 1407 | 1420 |
Knowledge DeepSeek-V3.1 leads
Chatgpt 4o Latest 20250326: 38.7 (#131), DeepSeek-V3.1: 43.0 (#86)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Expert | 1400 | 1403 |
| Confabulations | 16.6% | — |
| Vectara Hallucination Rate | — | 5.5% |
Multimodal Not comparable
Chatgpt 4o Latest 20250326: 38.9 (#54), DeepSeek-V3.1: —
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Vision | 1243 | — |
Multilingual Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 53.1 (#72), DeepSeek-V3.1: 51.8 (#100)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Non-English | 1419 | 1400 |
| LMArena Chinese | 1456 | 1470 |
| LMArena French | 1447 | 1447 |
| LMArena German | 1424 | 1412 |
| LMArena Japanese | 1406 | 1374 |
| LMArena Korean | 1397 | 1337 |
| LMArena Russian | 1429 | 1405 |
| LMArena Spanish | 1435 | 1429 |
Instruction Following Too close to call
Chatgpt 4o Latest 20250326: 74.2 (#102), DeepSeek-V3.1: 74.1 (#105)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1400 |
Long Context Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 43.1 (#104), DeepSeek-V3.1: 36.3 (#227)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Longer Query | 1413 | 1422 |
| Fiction.LiveBench | — | 52.8% |
Writing & Preference Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 62.8 (#68), DeepSeek-V3.1: 60.5 (#93)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Text | 1429 | 1420 |
| LMArena Creative Writing | 1406 | 1401 |
| EQ-Bench Creative Writing | 1501 | 1436 |
| LMArena Multi-Turn | 1454 | 1408 |
Frequently asked questions
Is Chatgpt 4o Latest 20250326 better than DeepSeek-V3.1?
Chatgpt 4o Latest 20250326 and DeepSeek-V3.1 score almost the same on the Noometry Index (43.2 vs 42.2), so choose on price, context window or the category you care about most.
Is Chatgpt 4o Latest 20250326 or DeepSeek-V3.1 better for coding?
Chatgpt 4o Latest 20250326 scores higher on coding benchmarks: 41.0 versus 39.8 in the Noometry coding category.
How many benchmarks do Chatgpt 4o Latest 20250326 and DeepSeek-V3.1 share?
19 benchmarks have published results for both models. Chatgpt 4o Latest 20250326 has 21 scored results on Noometry and DeepSeek-V3.1 has 27.