Compare / head-to-head
DeepSeek V3.2-Expvs
Hunyuan-A13B-Instruct
DeepSeek V3.2-Exp leads 2 of 2 shared benchmarks. Hunyuan-A13B-Instruct has the larger context window (262K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 0
DeepSeek V3.2-Exp leads
Cheaper per token
—
list price, input + output
Larger context
Hunyuan-A13B-Instruct
262K tokens
Providers
2 providers
DeepSeek · Tencent Hunyuan
DeepSeek V3.2-Exp
DeepSeek · released 2025-09-29
text
- Context
- 128K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 17 · 7 core
Hunyuan-A13B-Instruct
Tencent Hunyuan · released 2025-06-27
text
- Context
- 262K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 15 · 3 core
Quality
Benchmark matrix
2 shared · 15 only DeepSeek V3.2-Exp · 13 only Hunyuan-A13B-Instruct| Benchmark | DeepSeek V3.2-Exp | Hunyuan-A13B-Instruct | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| AIME 2025 | 89.3% ↗ | 76.8% ↗ | +12.5 pt | DeepSeek V3.2-Exp |
| GPQA-Diamond | 79.9% ↗ | 71.2% ↗ | +8.7 pt | DeepSeek V3.2-Exp |
| Only DeepSeek V3.2-Exp reports · 15 | ||||
| MMLU-Pro | 85% ↗ | not reported | — | — |
| Humanity's Last Exam (no tools) | 19.8% ↗ | not reported | — | — |
| LMArena Elo | 1424.9 ↗ | not reported | — | — |
| Aider-Polyglot | 74.5% ↗ | not reported | — | — |
| BrowseComp | 40.1% ↗ | not reported | — | — |
| BrowseComp-zh | 47.9% ↗ | not reported | — | — |
| HMMT 2025 | 83.6% ↗ | not reported | — | — |
| LiveCodeBench | 74.1% ↗ | not reported | — | — |
| LMArena WebDev (LMArena) | 1271.8 ↗ | not reported | — | — |
| SimpleQA (agentic tool use) | 97.1% ↗ | not reported | — | — |
| SWE Verified | 67.8% ↗ | not reported | — | — |
| SWE-bench Multilingual | 57.9% ↗ | not reported | — | — |
| Terminal-bench | 37.7% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 1034 ↗ | not reported | — | — |
| WeirdML (Håvard Tveit Ihle) | 39.5% ↗ | not reported | — | — |
| Only Hunyuan-A13B-Instruct reports · 13 | ||||
| AIME 2024 | not reported | 87.3% ↗ | — | — |
| ArtifactsBench | not reported | 43% ↗ | — | — |
| BBH | not reported | 89.1% ↗ | — | — |
| BFCL v3 | not reported | 78.3% ↗ | — | — |
| C3-Bench | not reported | 63.5% ↗ | — | — |
| ComplexFuncBench | not reported | 61.2% ↗ | — | — |
| Fullstackbench | not reported | 67.8% ↗ | — | — |
| IF-Eval | not reported | 84.7% ↗ | — | — |
| Livecodebench | not reported | 63.9% ↗ | — | — |
| MATH | not reported | 94.3% ↗ | — | — |
| OlympiadBench | not reported | 82.7% ↗ | — | — |
| ZebraLogic | not reported | 84.7% ↗ | — | — |
| τ-Bench | not reported | 54.7% ↗ | — | — |
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-Exp minus Hunyuan-A13B-Instruct 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-Exp | Hunyuan-A13B-Instruct | Edge |
|---|---|---|---|
| Context window | 128K tokens | 262K tokens | Hunyuan-A13B-Instruct |
| Max output | — | — | — |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text | text | Tie |
| Released | 2025-09-29 | 2025-06-27 | — |
| Cited benchmark scores | 17 | 15 | — |
Reliability
Provider status
Live from /statusMore matchups
DeepSeek V3.2-Exp vs …
Models sharing the most benchmarksMore matchups
Hunyuan-A13B-Instruct vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run DeepSeek V3.2-Exp and Hunyuan-A13B-Instruct on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.