Model comparison
Claude Haiku 5.5 vs DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 49.5 on the Noometry Index.
Last verified . 8 shared benchmarks.
DeepSeekSummary
- They share 8 benchmarks with published results for both. Claude Haiku 5.5 scores higher in 2 categories and DeepSeek V4.1 Flash in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 50.2 to 35.2.
- The biggest single-benchmark swing is NYT Connections (extended): 65.7% for Claude Haiku 5.5 and 89.6% for DeepSeek V4.1 Flash.
- Claude Haiku 5.5 is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.15 / $0.60 for DeepSeek V4.1 Flash.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 5.5 | DeepSeek V4.1 Flash | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 49.5 | 52.8 |
| Released | 2026-10-07 | 2026-09-09 |
| Weights | Proprietary | Open |
| Context window | 1M | 1M |
| Max output | 128K | 393K |
| Input $ / M tokens | $0.10 | $0.15 |
| Output $ / M tokens | $0.50 | $0.60 |
| Results tracked | 9 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
Claude Haiku 5.5: 49.2 (#50), DeepSeek V4.1 Flash: 52.9 (#32)
| Benchmark | Claude Haiku 5.5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena WebDev | 1587 | 1619 |
| SciCode | — | 51.9% |
| LMArena Coding | — | 1506 |
| ALE-Bench | — | 1,092 |
Agentic & Tool Use Not comparable
Claude Haiku 5.5: —, DeepSeek V4.1 Flash: 31.2 (#69)
| Benchmark | Claude Haiku 5.5 | DeepSeek V4.1 Flash |
|---|---|---|
| APEX-Agents | — | 39.5% |
| GDP.pdf | — | 19.8% |
Reasoning DeepSeek V4.1 Flash leads
Claude Haiku 5.5: 35.2 (#69), DeepSeek V4.1 Flash: 50.2 (#36)
| Benchmark | Claude Haiku 5.5 | DeepSeek V4.1 Flash |
|---|---|---|
| NYT Connections (extended) | 65.7% | 89.6% |
| Mystery Game Puzzles | 30% | 43% |
| CritPt | — | 14.3% |
| LMArena Hard Prompts | — | 1483 |
| DTBench | — | 89.9% |
| LMCA | — | 47% |
| Surface Evolver Bench | — | 46.3% |
| Epoch Capabilities Index | — | 154.9 |
Math Claude Haiku 5.5 leads
Claude Haiku 5.5: 73.6 (#18), DeepSeek V4.1 Flash: 66.7 (#25)
| Benchmark | Claude Haiku 5.5 | DeepSeek V4.1 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 75.1% | 67.4% |
| FrontierMath Tier 4 | 46.3% | 26.8% |
| OTIS Mock AIME 2024-2025 | 98.9% | 98.3% |
| ProofBench | — | 54% |
| LMArena Math | — | 1477 |
Knowledge DeepSeek V4.1 Flash leads
Claude Haiku 5.5: 50.8 (#70), DeepSeek V4.1 Flash: 57.9 (#38)
| Benchmark | Claude Haiku 5.5 | DeepSeek V4.1 Flash |
|---|---|---|
| GPQA Diamond | 89.6% | 89.8% |
| SimpleQA Verified | 23.8% | — |
| LMArena Expert | — | 1506 |
Multimodal Claude Haiku 5.5 leads
Claude Haiku 5.5: 43.7 (#21), DeepSeek V4.1 Flash: 39.1 (#61)
| Benchmark | Claude Haiku 5.5 | DeepSeek V4.1 Flash |
|---|---|---|
| Furniture Assembly | 47.5% | 34.2% |
| LMArena Vision | — | 1277 |
Multilingual Not comparable
Claude Haiku 5.5: —, DeepSeek V4.1 Flash: 55.0 (#35)
| Benchmark | Claude Haiku 5.5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Non-English | — | 1448 |
| LMArena Chinese | — | 1497 |
| LMArena French | — | 1452 |
| LMArena German | — | 1484 |
| LMArena Japanese | — | 1412 |
| LMArena Korean | — | 1452 |
| LMArena Russian | — | 1471 |
| LMArena Spanish | — | 1459 |
Instruction Following Not comparable
Claude Haiku 5.5: —, DeepSeek V4.1 Flash: 77.3 (#26)
| Benchmark | Claude Haiku 5.5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1474 |
Long Context Not comparable
Claude Haiku 5.5: —, DeepSeek V4.1 Flash: 45.2 (#47)
| Benchmark | Claude Haiku 5.5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Longer Query | — | 1475 |
Writing & Preference Not comparable
Claude Haiku 5.5: —, DeepSeek V4.1 Flash: 65.4 (#48)
| Benchmark | Claude Haiku 5.5 | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Text | — | 1462 |
| LMArena Creative Writing | — | 1435 |
| EQ-Bench Creative Writing | — | 1540 |
| LMArena Multi-Turn | — | 1457 |
Frequently asked questions
Is Claude Haiku 5.5 better than DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 49.5 on the Noometry Index.
Which is cheaper, Claude Haiku 5.5 or DeepSeek V4.1 Flash?
Claude Haiku 5.5 is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; DeepSeek V4.1 Flash lists at $0.15 and $0.60.
Is Claude Haiku 5.5 or DeepSeek V4.1 Flash better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 49.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Haiku 5.5 and DeepSeek V4.1 Flash share?
8 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and DeepSeek V4.1 Flash has 37.