Model comparison
DeepSeek-V2.5 (Sep 2024) vs GPT-6.1 Sol
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 37.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeekSummary
- They share 12 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and GPT-6.1 Sol in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 35.9.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | GPT-6.1 Sol | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 37.6 | 65.6 |
| Released | 2024-09-06 | 2026-09-29 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $10 |
| Results tracked | 22 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), GPT-6.1 Sol: 63.2 (#8)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-6.1 Sol |
|---|---|---|
| LMArena Coding | 1309 | 1487 |
| DeepSWE | — | 75.2% |
| FrontierCode | — | 50.2% |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1755 |
| SciCode | — | 55.8% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, GPT-6.1 Sol: 39.6 (#26)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-6.1 Sol |
|---|---|---|
| APEX-Agents | — | 60% |
| GDP.pdf | — | 32% |
Reasoning GPT-6.1 Sol leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), GPT-6.1 Sol: 81.9 (#2)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-6.1 Sol |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1466 |
| ARC-AGI-2 | — | 94.2% |
| NYT Connections (extended) | — | 95.5% |
| ARC-AGI-1 | — | 98.5% |
| CritPt | — | 31.7% |
| Chess Puzzles | — | 61% |
| EBR-Bench | — | 54.3% |
| Mystery Game Puzzles | — | 80% |
| Epoch Capabilities Index | — | 166.09 |
Math GPT-6.1 Sol leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), GPT-6.1 Sol: 93.7 (#1)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-6.1 Sol |
|---|---|---|
| LMArena Math | 1288 | 1464 |
| FrontierMath (Tiers 1-3) | — | 93.7% |
| FrontierMath Tier 4 | — | 100% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 99% |
Knowledge GPT-6.1 Sol leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), GPT-6.1 Sol: 71.8 (#4)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-6.1 Sol |
|---|---|---|
| LMArena Expert | 1266 | 1502 |
| GPQA Diamond | — | 95.4% |
| SimpleQA Verified | — | 73.9% |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, GPT-6.1 Sol: 52.7 (#5)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-6.1 Sol |
|---|---|---|
| LMArena Vision | — | 1288 |
| Furniture Assembly | — | 80% |
Multilingual GPT-6.1 Sol leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), GPT-6.1 Sol: 54.3 (#46)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-6.1 Sol |
|---|---|---|
| LMArena Non-English | 1273 | 1438 |
| LMArena Chinese | 1318 | 1477 |
| LMArena Russian | 1289 | 1455 |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |
Instruction Following GPT-6.1 Sol leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), GPT-6.1 Sol: 77.0 (#29)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-6.1 Sol |
|---|---|---|
| LMArena Instruction Following | 1280 | 1468 |
Long Context GPT-6.1 Sol leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), GPT-6.1 Sol: 44.9 (#54)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-6.1 Sol |
|---|---|---|
| LMArena Longer Query | 1301 | 1465 |
Writing & Preference GPT-6.1 Sol leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), GPT-6.1 Sol: 63.6 (#63)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | GPT-6.1 Sol |
|---|---|---|
| LMArena Text | 1294 | 1447 |
| LMArena Creative Writing | 1285 | 1432 |
| LMArena Multi-Turn | 1297 | 1449 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than GPT-6.1 Sol?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or GPT-6.1 Sol better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and GPT-6.1 Sol share?
12 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and GPT-6.1 Sol has 34.