Model comparison
Claude Haiku 5.5 vs DeepSeek-V3.2-Exp
Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 44.3 on the Noometry Index.
Last verified . 4 shared benchmarks.
DeepSeekSummary
- They share 4 benchmarks with published results for both. Claude Haiku 5.5 scores higher in 3 categories and DeepSeek-V3.2-Exp in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 5.5 leads 73.6 to 41.7.
- The biggest single-benchmark swing is NYT Connections (extended): 65.7% for Claude Haiku 5.5 and 36.7% for DeepSeek-V3.2-Exp.
- Claude Haiku 5.5 is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.26 / $0.38 for DeepSeek-V3.2-Exp.
- Claude Haiku 5.5 accepts more context: 1M tokens versus 164K.
- DeepSeek-V3.2-Exp has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 5.5 | DeepSeek-V3.2-Exp | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 49.5 | 44.3 |
| Released | 2026-10-07 | 2025-09-29 |
| Weights | Proprietary | Open |
| Context window | 1M | 164K |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.10 | $0.26 |
| Output $ / M tokens | $0.50 | $0.38 |
| Results tracked | 9 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 5.5 leads
Claude Haiku 5.5: 49.2 (#50), DeepSeek-V3.2-Exp: 46.5 (#65)
| Benchmark | Claude Haiku 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena WebDev | 1587 | 1362 |
| SWE-bench Verified (bash only) | — | 70% |
| Aider Polyglot | — | 74.2% |
| SWE-bench Multilingual | — | 59% |
| SciCode | — | 38.9% |
| WeirdML | — | 39.5% |
| LMArena Coding | — | 1454 |
Agentic & Tool Use Not comparable
Claude Haiku 5.5: —, DeepSeek-V3.2-Exp: 32.7 (#59)
| Benchmark | Claude Haiku 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| Terminal-Bench | — | 39.6% |
| APEX-Agents | — | 21.3% |
| Berkeley Function Calling Leaderboard | — | 56.7% |
| TheAgentCompany | — | 42.9% |
| Vending-Bench 2 | — | 1,034 |
Reasoning Claude Haiku 5.5 leads
Claude Haiku 5.5: 35.2 (#69), DeepSeek-V3.2-Exp: 22.1 (#208)
| Benchmark | Claude Haiku 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| NYT Connections (extended) | 65.7% | 36.7% |
| ARC-AGI-2 | — | 4% |
| Kagi LLM Benchmark | — | 52.2% |
| ARC-AGI-1 | — | 57% |
| CritPt | — | 2.9% |
| Chess Puzzles | — | 14% |
| Thematic Generalization | — | 65% |
| LMArena Hard Prompts | — | 1434 |
| Mystery Game Puzzles | 30% | — |
| DTBench | — | 87.7% |
| LMCA | — | 29.1% |
| Epoch Capabilities Index | — | 146.27 |
Math Claude Haiku 5.5 leads
Claude Haiku 5.5: 73.6 (#18), DeepSeek-V3.2-Exp: 41.7 (#87)
| Benchmark | Claude Haiku 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.9% | 87.8% |
| FrontierMath (Tiers 1-3) | 75.1% | — |
| FrontierMath Tier 4 | 46.3% | — |
| MathArena Final-Answer Competitions | — | 57.7% |
| ProofBench | — | 8% |
| LMArena Math | — | 1435 |
| FrontierMath (Feb 2025 set) | — | 22.1% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Too close to call
Claude Haiku 5.5: 50.8 (#70), DeepSeek-V3.2-Exp: 51.7 (#66)
| Benchmark | Claude Haiku 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| GPQA Diamond | 89.6% | 83.4% |
| SimpleQA Verified | 23.8% | — |
| Vectara Hallucination Rate | — | 5.3% |
| LMArena Expert | — | 1436 |
Multimodal Not comparable
Claude Haiku 5.5: 43.7 (#21), DeepSeek-V3.2-Exp: —
| Benchmark | Claude Haiku 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| Furniture Assembly | 47.5% | — |
Multilingual Not comparable
Claude Haiku 5.5: —, DeepSeek-V3.2-Exp: 52.2 (#90)
| Benchmark | Claude Haiku 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Non-English | — | 1409 |
| LMArena Chinese | — | 1461 |
| LMArena French | — | 1433 |
| LMArena German | — | 1440 |
| LMArena Japanese | — | 1374 |
| LMArena Korean | — | 1371 |
| LMArena Russian | — | 1424 |
| LMArena Spanish | — | 1440 |
Instruction Following Not comparable
Claude Haiku 5.5: —, DeepSeek-V3.2-Exp: 74.5 (#93)
| Benchmark | Claude Haiku 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Instruction Following | — | 1413 |
Long Context Not comparable
Claude Haiku 5.5: —, DeepSeek-V3.2-Exp: 47.6 (#16)
| Benchmark | Claude Haiku 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| Fiction.LiveBench | — | 83.3% |
| CL-bench | — | 13.2% |
| CL-bench Life | — | 9.5% |
| LMArena Longer Query | — | 1428 |
Writing & Preference Not comparable
Claude Haiku 5.5: —, DeepSeek-V3.2-Exp: 62.4 (#77)
| Benchmark | Claude Haiku 5.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| LMArena Text | — | 1425 |
| LMArena Creative Writing | — | 1403 |
| EQ-Bench Creative Writing | — | 1515 |
| LMArena Multi-Turn | — | 1427 |
Frequently asked questions
Is Claude Haiku 5.5 better than DeepSeek-V3.2-Exp?
Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 44.3 on the Noometry Index.
Which is cheaper, Claude Haiku 5.5 or DeepSeek-V3.2-Exp?
Claude Haiku 5.5 is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; DeepSeek-V3.2-Exp lists at $0.26 and $0.38.
Is Claude Haiku 5.5 or DeepSeek-V3.2-Exp better for coding?
Claude Haiku 5.5 scores higher on coding benchmarks: 49.2 versus 46.5 in the Noometry coding category.
Which has the bigger context window?
Claude Haiku 5.5 does, with 1M tokens against 164K.
How many benchmarks do Claude Haiku 5.5 and DeepSeek-V3.2-Exp share?
4 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and DeepSeek-V3.2-Exp has 49.