Compare / head-to-head
DeepSeek V3.2-Specialevs
o3
DeepSeek V3.2-Speciale and o3 split their 4 shared benchmarks evenly.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 2
even split
Cheaper per token
—
list price, input + output
Larger context
—
unknown
Providers
2 providers
DeepSeek · OpenAI
DeepSeek V3.2-Speciale
DeepSeek · released 2025-12-01
text
- Context
- —
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 9 · 4 core
Quality
Benchmark matrix
4 shared · 5 only DeepSeek V3.2-Speciale · 13 only o3| Benchmark | DeepSeek V3.2-Speciale | o3 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 4 | ||||
| GPQA Diamond | 85.7% ↗ | 81.8% ↗epoch run | +3.9 pt | DeepSeek V3.2-Speciale |
| AIME 2025 | 96% ↗ | 89.2% ↗matharena ⚠ | +6.8 pt | DeepSeek V3.2-Speciale |
| SimpleBench (SimpleBench) | 52.6% ↗ | 53.1% ↗ | -0.5 pt | o3 |
| WeirdML (Håvard Tveit Ihle) | 46.7% ↗ | 52.4% ↗ | -5.7 pt | o3 |
| Only DeepSeek V3.2-Speciale reports · 5 | ||||
| HLE (text-only) | 30.6% ↗ | not reported | — | — |
| HMMT Feb 2025 | 99.2% ↗ | not reported | — | — |
| HMMT Nov 2025 | 94.4% ↗ | not reported | — | — |
| IMOAnswerBench | 84.5% ↗ | not reported | — | — |
| LiveCodeBench (Pass@1-COT) | 88.7% ↗ | not reported | — | — |
| Only o3 reports · 13 | ||||
| SWE-bench Verified | not reported | 69.1% ↗ | — | — |
| LMArena Elo | not reported | 1431.6 ↗ | — | — |
| Chess Puzzles (Epoch AI run) | not reported | 38% ↗epoch run | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 33.3% ↗epoch run | — | — |
| GSO Opt@1 (GSO) | not reported | 3.9% ↗ | — | — |
| LMArena Vision (LMArena) | not reported | 1215.7 ↗ | — | — |
| MATH Level 5 (Epoch AI run) | not reported | 97.8% ↗epoch run | — | — |
| Mystery Game Puzzles (Epoch AI run) | not reported | 29% ↗epoch run | — | — |
| OSWorld-Verified (XLANG) | not reported | 23% ↗ | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | not reported | 84.4% ↗epoch run | — | — |
| SAGE (Vals AI) | not reported | 41.8% ↗ | — | — |
| SimpleQA Verified | not reported | 49.4% ↗epoch run | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 62.3% ↗epoch run | — | — |
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 V3.2-Speciale minus o3 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 V3.2-Speciale | o3 | Edge |
|---|---|---|---|
| Context window | — | 200K tokens | — |
| Max output | — | 100K tokens | — |
| Input price / 1M | — | $2 ↗ | — |
| Output price / 1M | — | $8 ↗ | — |
| Cached input / 1M | — | $0.5 ↗ | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $10 | — |
| Modalities | text | text · vision | o3 |
| Released | 2025-12-01 | 2025-04-16 | — |
| Cited benchmark scores | 9 | 22 | — |
Reliability
Provider status
Live from /statusMore matchups
DeepSeek V3.2-Speciale vs …
Models sharing the most benchmarksMore matchups
o3 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run DeepSeek V3.2-Speciale and o3 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.