Across 7 comparable benchmarks, Claude Opus 4.6 has better reported results on 6 and worse on 1.
Moderate evidence7 of 7 shared results countedHow we compare
DeepSeek V3.2 Speciale is no longer available through its official API. API prices for this version are not shown.
Price basis: Listed rates vs standard rates. The price section below shows the applicable periods.
| Fact | DeepSeek V3.2 Speciale | Claude Opus 4.6 |
|---|---|---|
| Context window | 128K tokens | 1M tokens |
| Input / 1M | — | $5.00 |
| Output / 1M | — | $25.00 |
| Blended (4:1) | — | $5.76 |
| Status | Retired | Available |
| Released | December 1, 2025 | February 5, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 2 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Split 1–1 of 2 counted
Claude Opus 4.6 ahead on 1 of 1 counted
No fixed-scale average — see the rows in Benchmark results
Claude Opus 4.6 ahead on 1 of 1 counted
Claude Opus 4.6 ahead on 1 of 1 counted
No fixed-scale average — see the rows in Benchmark results
Claude Opus 4.6 ahead on 1 of 1 counted
No fixed-scale average — see the rows in Benchmark results
No shared comparable results for Computer & tool use, Research & search, Long context, Multimodal, Cybersecurity.
Published scores, with matching modes where available. Gaps show DeepSeek V3.2 Speciale relative to Claude Opus 4.6. Reading the results
| Benchmark | DeepSeek V3.2 Speciale | Claude Opus 4.6 | Gap |
|---|---|---|---|
| LiveCodeBenchAlgorithmic Coding · Pass @K | 89.6Thinking · no tools | 76.0≠Extended · no tools | 1.18×#10 vs #42 of 113 |
| Terminal Bench HardAgentic Development · Accuracy | 34.8Thinking · tools | 48.5≠Normal · tools | −13.7 pts#50 vs #14 of 157 |
| SimpleBenchCommonsense · Score (AVG@5) | 52.6Normal · no tools | 67.6Normal · no tools | 0.78×#58 vs #28 of 102 |
| AIME2025Mathematics · Accuracy | 96.0Thinking · no tools | 99.8≠Extended · no tools | −3.8 pts#20 vs #7 of 86 |
| CritPtScientific Reasoning · Score | 7.4Thinking · no tools | 12.6≠Max · no tools | 0.59×#64 vs #48 of 134 |
| Creative WritingWriting | 1277Normal · no tools | 1810Normal · no tools | 0.71×#87 vs #24 of 121 |
| HLEKnowledge Exams · Accuracy | 30.6Thinking · no tools | 53.0≠Extended · tools + web | −22.4 pts#87 vs #37 of 151 |
Algorithmic Coding · Pass @K
Agentic Development · Accuracy
Commonsense · Score (AVG@5)
Mathematics · Accuracy
Scientific Reasoning · Score
Writing
Knowledge Exams · Accuracy
A dash means no result is available.
| Benchmark | DeepSeek V3.2 Speciale | Claude Opus 4.6 |
|---|---|---|
| AIME 2026 | — | 96.7 |
| FrontierMath | — | 40.7 |
| FrontierMath - Tier 4 | — | 22.9 |
| FrontierMath Tier 4 v2 | — | 26.8 |
| FrontierMath v2 | — | 66.0 |
| GPQA Diamond | — | 91.3 |
| HLE-Verified | — | 46.8 |
| HMMT Feb 2026 | — | 96.2 |
| MATH-500 | — | 97.6 |
| MathArena Apex | — | 34.5 |
| MMLU-Pro | 86.3 | — |
| Riemann-bench | — | 27.2 |
| APEX-SWE | — | 41.8 |
| CodeForces | 2701 | — |
| FrontierCode 1.1 | — | 43.7 |
| FrontierSWE v1 | — | 48.9 |
| GSO | — | 41.2 |
| HumanEval | — | 95.0 |
| SWE-bench Multilingual | — | 77.8 |
| SWE-Bench Pro - Commercial | — | 47.1 |
| SWE-Bench Pro - Public | — | 51.9 |
| SWE-bench Verified | — | 80.8 |
| Terminal Bench 2.0 | — | 65.4 |
| Vibe Code Bench v1.1 | — | 57.6 |
| WeirdML v2 | — | 78.0 |
| APEX-Agents | — | 46.3 |
| MCP-Atlas | — | 76.8 |
| OSWorld-Verified | — | 72.7 |
| Pinch Bench | — | 87.4 |
| PinchBench v2 | — | 69.9 |
| ECI | — | 155 |
| LiveBench | — | 74.5 |
| Text Arena (Coding) | — | 1555 |
| Context Arena | — | 85.2 |
| EBR-bench | — | 12.7 |
| MMMU-Pro | — | 77.3 |
| SAGE | — | 51.6 |
| τ²-Bench | — | 91.9 |
| τ²-Bench - Telecom | — | 99.3 |
| τ³-Banking | — | 27.3 |
| ARC-AGI-1 | — | 94.0 |
| ARC-AGI-2 | — | 69.2 |
| ARC-AGI-3 | — | 0.51 |
| Vending-Bench 2 | — | 8018 |
| BrowseComp | — | 84.0 |
| SimpleQA | — | 72.0 |
| MedCode | — | 49.1 |
| MedScribe | — | 86.7 |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
A blended cost needs a published input and output price on both sides, and one of these two does not have them yet.
DeepSeek V3.2 Speciale: Listed text rates; pricing tier not confirmed.
Claude Opus 4.6: Standard pricing. Anthropic official pricing (platform.claude.com/docs/en/about-claude/pricing) verified 2026-10-21; full 1M context at standard price
| Price / 1M tokens | DeepSeek V3.2 Speciale | Claude Opus 4.6 | Ratio |
|---|---|---|---|
| Input | — | $5.00 | — |
| Output | — | $25.00 | — |
| Cached input | — | $0.50 | — |
| Cache write | — | — | — |
| Blended | — | $5.76 | — |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
| Benchmark | DeepSeek V3.2 Speciale | Claude Opus 4.6 |
|---|---|---|
| AIME 2026 | Not reported | |
| ARC-AGI-1 | Not reported | |
| ARC-AGI-2 | Not reported | $2.7209 / task Average · ARC-AGI-2 Score: 66.3 Thinking Medium (No Tools) |
| FrontierCode 1.1 | Not reported | $3.1206 / task Average · Weighted rubric score: 42.9 Max (With Tools) · frontiercode-1-1-extended $3.7346 / task Average · Weighted rubric score: 26.9 Max (With Tools) · frontiercode-1-1-main $3.9796 / task Average · Weighted rubric score: 26.6 Thinking High (With Tools) · frontiercode-1-1-main 5 more settings$3.2978 / task Average · Weighted rubric score: 43.7 Thinking High (With Tools) · frontiercode-1-1-extended $1.8406 / task Average · Weighted rubric score: 32.9 Thinking Low (With Tools) · frontiercode-1-1-extended $2.101 / task Average · Weighted rubric score: 18.3 Thinking Low (With Tools) · frontiercode-1-1-main $2.3912 / task Average · Weighted rubric score: 38.6 Thinking Medium (With Tools) · frontiercode-1-1-extended $2.7941 / task Average · Weighted rubric score: 23.7 Thinking Medium (With Tools) · frontiercode-1-1-main |
| Attribute | DeepSeek V3.2 Speciale | Claude Opus 4.6 |
|---|---|---|
| Availability | Retired | Available |
| Provider | DeepSeek-AI | Anthropic |
| Model type | Reasoning model | Reasoning model |
| First release | December 1, 2025 | February 5, 2026 |
| Context window | 128K tokens | 1M tokens |
| Max output | 32K tokens | 64K tokens |
| Architecture | Undisclosed | Undisclosed |
| Documented capabilities | Reasoning, Multilingual | Reasoning, Multilingual |
| Knowledge cutoff | — | 2025-05 |
| Input modalities | Text | Text, Image |
| Output modalities | Text | Text |
| Weights | Open weights | Closed / API only |
| Licence | MIT License | — |
| Commercial use | Commercial use allowed | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used DeepSeek V3.2 Speciale or Claude Opus 4.6? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.