Compare / head-to-head
DeepSeek V3.1-Terminusvs
GPT-6 Luna
GPT-6 Luna leads 1 of 1 shared benchmark. GPT-6 Luna has the larger context window (1.1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 1
GPT-6 Luna leads
Cheaper per token
—
list price, input + output
Larger context
GPT-6 Luna
1.1M tokens
Providers
2 providers
DeepSeek · OpenAI
DeepSeek V3.1-Terminus
DeepSeek · released 2025-09-22
text
- Context
- 128K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 12 · 5 core
GPT-6 Luna
OpenAI · released 2026-09-22
textvision
Quality
Benchmark matrix
1 shared · 11 only DeepSeek V3.1-Terminus · 21 only GPT-6 Luna| Benchmark | DeepSeek V3.1-Terminus | GPT-6 Luna | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 1 | ||||
| LMArena Elo | 1417.2 ↗ | 1442.9 ↗ | -25.7 | GPT-6 Luna |
| Only DeepSeek V3.1-Terminus reports · 11 | ||||
| MMLU-Pro | 85% ↗ | not reported | — | — |
| Humanity's Last Exam (no tools) | 21.7% ↗ | not reported | — | — |
| Aider-Polyglot | 76.1% ↗ | not reported | — | — |
| BrowseComp | 38.5% ↗ | not reported | — | — |
| BrowseComp-zh | 45% ↗ | not reported | — | — |
| GPQA-Diamond | 80.7% ↗ | not reported | — | — |
| LiveCodeBench | 74.9% ↗ | not reported | — | — |
| SimpleQA (agentic tool use) | 96.8% ↗ | not reported | — | — |
| SWE Verified | 68.4% ↗ | not reported | — | — |
| SWE-bench Multilingual | 57.8% ↗ | not reported | — | — |
| Terminal-bench | 36.7% ↗ | not reported | — | — |
| Only GPT-6 Luna reports · 21 | ||||
| GPQA Diamond | not reported | 90.5% ↗epoch run | — | — |
| APEX-Agents (Mercor) | not reported | 44.3% ↗ | — | — |
| Chess Puzzles (Epoch AI run) | not reported | 31% ↗epoch run | — | — |
| DeepSWE v1.1 | not reported | 66.6% ↗ | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 56.1% ↗epoch run | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 78.9% ↗epoch run | — | — |
| Furniture Assembly (Epoch AI run) | not reported | 44.2% ↗epoch run | — | — |
| LiveBench Agentic Coding (LiveBench) | not reported | 51.2% ↗ | — | — |
| LiveBench Coding (LiveBench) | not reported | 79% ↗ | — | — |
| LiveBench Data Analysis (LiveBench) | not reported | 73.4% ↗ | — | — |
| LiveBench Instruction Following (LiveBench) | not reported | 55.9% ↗ | — | — |
| LiveBench Language (LiveBench) | not reported | 73.8% ↗ | — | — |
| LiveBench Mathematics (LiveBench) | not reported | 89.1% ↗ | — | — |
| LiveBench Reasoning (LiveBench) | not reported | 81.8% ↗ | — | — |
| LMArena Agent (LMArena) | not reported | 0.0135 ↗ | — | — |
| LMArena WebDev (LMArena) | not reported | 1578.7 ↗ | — | — |
| Mystery Game Puzzles (Epoch AI run) | not reported | 7% ↗epoch run | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | not reported | 98.9% ↗epoch run | — | — |
| SAGE (Vals AI) | not reported | 48.1% ↗ | — | — |
| SimpleQA Verified | not reported | 41.4% ↗epoch run | — | — |
| Terminal-Bench 4.0 (Vals AI) | not reported | 13.6% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is DeepSeek V3.1-Terminus minus GPT-6 Luna in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | DeepSeek V3.1-Terminus | GPT-6 Luna | Edge |
|---|---|---|---|
| Context window | 128K tokens | 1.1M tokens | GPT-6 Luna |
| Max output | — | 128K tokens | — |
| Input price / 1M | — | $0.1 ↗ | — |
| Output price / 1M | — | $0.5 ↗ | — |
| Cached input / 1M | — | $0.01 ↗ | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $0.6 | — |
| Modalities | text | text · vision | GPT-6 Luna |
| Released | 2025-09-22 | 2026-09-22 | — |
| Cited benchmark scores | 12 | 22 | — |
Reliability
Provider status
Live from /statusMore matchups
DeepSeek V3.1-Terminus vs …
Models sharing the most benchmarksMore matchups
GPT-6 Luna vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run DeepSeek V3.1-Terminus and GPT-6 Luna on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.