Model comparison
DeepSeek-V3.1-Terminus vs GPT-6.1 Sol
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 8.8× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
DeepSeekSummary
- They share 12 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 0 categories and GPT-6.1 Sol in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6.1 Sol leads 81.9 to 26.4.
- The biggest single-benchmark swing is CritPt: 1.7% for DeepSeek-V3.1-Terminus and 31.7% for GPT-6.1 Sol.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 164K.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | GPT-6.1 Sol | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 43.1 | 65.6 |
| Released | 2025-09-22 | 2026-09-29 |
| Weights | Open | Proprietary |
| Context window | 164K | 1.05M |
| Max output | 147K | 128K |
| Input $ / M tokens | $0.27 | $2 |
| Output $ / M tokens | $1 | $10 |
| Results tracked | 16 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
DeepSeek-V3.1-Terminus: 42.0 (#113), GPT-6.1 Sol: 63.2 (#8)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-6.1 Sol |
|---|---|---|
| SciCode | 40.6% | 55.8% |
| LMArena Coding | 1426 | 1487 |
| DeepSWE | — | 75.2% |
| FrontierCode | — | 50.2% |
| LMArena WebDev | — | 1755 |
| ALE-Bench | 745.17 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, GPT-6.1 Sol: 39.6 (#26)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-6.1 Sol |
|---|---|---|
| APEX-Agents | — | 60% |
| GDP.pdf | — | 32% |
Reasoning GPT-6.1 Sol leads
DeepSeek-V3.1-Terminus: 26.4 (#133), GPT-6.1 Sol: 81.9 (#2)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-6.1 Sol |
|---|---|---|
| CritPt | 1.7% | 31.7% |
| LMArena Hard Prompts | 1426 | 1466 |
| ARC-AGI-2 | — | 94.2% |
| Kagi LLM Benchmark | 57.4% | — |
| NYT Connections (extended) | — | 95.5% |
| ARC-AGI-1 | — | 98.5% |
| Chess Puzzles | — | 61% |
| EBR-Bench | — | 54.3% |
| Mystery Game Puzzles | — | 80% |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
| Epoch Capabilities Index | — | 166.09 |
Math GPT-6.1 Sol leads
DeepSeek-V3.1-Terminus: 38.5 (#137), GPT-6.1 Sol: 93.7 (#1)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-6.1 Sol |
|---|---|---|
| LMArena Math | 1402 | 1464 |
| FrontierMath (Tiers 1-3) | — | 93.7% |
| FrontierMath Tier 4 | — | 100% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 99% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, GPT-6.1 Sol: 71.8 (#4)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-6.1 Sol |
|---|---|---|
| GPQA Diamond | — | 95.4% |
| SimpleQA Verified | — | 73.9% |
| LMArena Expert | — | 1502 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, GPT-6.1 Sol: 52.7 (#5)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-6.1 Sol |
|---|---|---|
| LMArena Vision | — | 1288 |
| Furniture Assembly | — | 80% |
Multilingual GPT-6.1 Sol leads
DeepSeek-V3.1-Terminus: 52.1 (#92), GPT-6.1 Sol: 54.3 (#46)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-6.1 Sol |
|---|---|---|
| LMArena Non-English | 1407 | 1438 |
| LMArena Russian | 1436 | 1455 |
| LMArena Chinese | — | 1477 |
Instruction Following GPT-6.1 Sol leads
DeepSeek-V3.1-Terminus: 74.0 (#106), GPT-6.1 Sol: 77.0 (#29)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-6.1 Sol |
|---|---|---|
| LMArena Instruction Following | 1404 | 1468 |
Long Context GPT-6.1 Sol leads
DeepSeek-V3.1-Terminus: 43.4 (#97), GPT-6.1 Sol: 44.9 (#54)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-6.1 Sol |
|---|---|---|
| LMArena Longer Query | 1421 | 1465 |
Writing & Preference GPT-6.1 Sol leads
DeepSeek-V3.1-Terminus: 61.0 (#92), GPT-6.1 Sol: 63.6 (#63)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-6.1 Sol |
|---|---|---|
| LMArena Text | 1419 | 1447 |
| LMArena Creative Writing | 1403 | 1432 |
| LMArena Multi-Turn | 1411 | 1449 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than GPT-6.1 Sol?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 8.8× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1-Terminus or GPT-6.1 Sol?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; GPT-6.1 Sol lists at $2 and $10.
Is DeepSeek-V3.1-Terminus or GPT-6.1 Sol better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 42.0 in the Noometry coding category.
Which has the bigger context window?
GPT-6.1 Sol does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and GPT-6.1 Sol share?
12 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and GPT-6.1 Sol has 34.