Model comparison
Chatgpt 4o Latest 20250326 vs DeepSeek-R1
Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.8 to 42.3 on the Noometry Index.
Last verified . 20 shared benchmarks.
DeepSeekSummary
- They share 20 benchmarks with published results for both. Chatgpt 4o Latest 20250326 scores higher in 4 categories and DeepSeek-R1 in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Chatgpt 4o Latest 20250326 leads 33.8 to 18.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 75% for Chatgpt 4o Latest 20250326 and 69.4% for DeepSeek-R1.
Side by side
| Chatgpt 4o Latest 20250326 | DeepSeek-R1 | |
|---|---|---|
| Provider | OpenAI | DeepSeek |
| Noometry Index | 43.8 | 42.3 |
| Released | — | 2025-01-20 |
| Weights | Proprietary | Proprietary |
| Context window | — | 164K |
| Max output | — | 64K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $2.15 |
| Results tracked | 21 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
Chatgpt 4o Latest 20250326: 41.6 (#122), DeepSeek-R1: 46.3 (#68)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-R1 |
|---|---|---|
| LMArena Coding | 1413 | 1427 |
| Aider Polyglot | — | 71.4% |
| SciCode | — | 35.7% |
| WeirdML | — | 41.6% |
| LiveBench Coding | — | 66.7% |
| ALE-Bench | — | 804.12 |
| AlgoTune | — | 1.7 |
Agentic & Tool Use Not comparable
Chatgpt 4o Latest 20250326: —, DeepSeek-R1: 30.7 (#75)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-R1 |
|---|---|---|
| DeepResearch Bench | — | 35.1% |
| BALROG | — | 34.9% |
| METR Time Horizons | — | 53.8% |
Reasoning Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 33.8 (#71), DeepSeek-R1: 18.6 (#278)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-R1 |
|---|---|---|
| Kagi LLM Benchmark | 75% | 69.4% |
| LMArena Hard Prompts | 1424 | 1416 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 40.8% |
| ARC-AGI-1 | — | 21.2% |
| CritPt | — | 1.1% |
| LiveBench Reasoning | — | 83.2% |
| LiveBench Data Analysis | — | 69.8% |
| Epoch Capabilities Index | — | 141.29 |
| ForecastBench | — | 60 |
| LiveBench | — | 71.6% |
Math DeepSeek-R1 leads
Chatgpt 4o Latest 20250326: 38.6 (#134), DeepSeek-R1: 43.8 (#79)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-R1 |
|---|---|---|
| LMArena Math | 1407 | 1400 |
| OTIS Mock AIME 2024-2025 | — | 66.4% |
| Omni-MATH | — | 42.4% |
| LiveBench Math | — | 80.7% |
| MATH Level 5 | — | 96.6% |
Knowledge DeepSeek-R1 leads
Chatgpt 4o Latest 20250326: 39.2 (#137), DeepSeek-R1: 44.5 (#87)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-R1 |
|---|---|---|
| Confabulations | 16.6% | 12.7% |
| LMArena Expert | 1401 | 1394 |
| GPQA Diamond | — | 76.3% |
| MMLU-Pro | — | 79.3% |
| Vectara Hallucination Rate | — | 11.3% |
| GPQA (HELM) | — | 66.6% |
Multimodal Not comparable
Chatgpt 4o Latest 20250326: 39.6 (#58), DeepSeek-R1: —
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-R1 |
|---|---|---|
| LMArena Vision | 1243 | — |
Multilingual Too close to call
Chatgpt 4o Latest 20250326: 52.9 (#76), DeepSeek-R1: 52.4 (#85)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-R1 |
|---|---|---|
| LMArena Non-English | 1419 | 1412 |
| LMArena Chinese | 1457 | 1442 |
| LMArena French | 1446 | 1417 |
| LMArena German | 1423 | 1404 |
| LMArena Japanese | 1405 | 1391 |
| LMArena Korean | 1396 | 1360 |
| LMArena Russian | 1429 | 1423 |
| LMArena Spanish | 1434 | 1411 |
Instruction Following Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 74.0 (#107), DeepSeek-R1: 72.0 (#143)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-R1 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1382 |
| LiveBench Instruction Following | — | 80.5% |
| IFEval | — | 78.4% |
Long Context DeepSeek-R1 leads
Chatgpt 4o Latest 20250326: 43.1 (#107), DeepSeek-R1: 45.4 (#36)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-R1 |
|---|---|---|
| LMArena Longer Query | 1413 | 1391 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 62.6 (#72), DeepSeek-R1: 61.4 (#88)
| Benchmark | Chatgpt 4o Latest 20250326 | DeepSeek-R1 |
|---|---|---|
| LMArena Text | 1429 | 1428 |
| LMArena Creative Writing | 1405 | 1405 |
| EQ-Bench Creative Writing | 1501 | 1500 |
| LMArena Multi-Turn | 1454 | 1405 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 82.8% |
| LiveBench Language | — | 48.5% |
Frequently asked questions
Is Chatgpt 4o Latest 20250326 better than DeepSeek-R1?
Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.8 to 42.3 on the Noometry Index.
Is Chatgpt 4o Latest 20250326 or DeepSeek-R1 better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 41.6 in the Noometry coding category.
How many benchmarks do Chatgpt 4o Latest 20250326 and DeepSeek-R1 share?
20 benchmarks have published results for both models. Chatgpt 4o Latest 20250326 has 21 scored results on Noometry and DeepSeek-R1 has 52.