Model comparison
Claude Haiku 4.5 vs DeepSeek-V2 (MoE-236B, May 2024)
Claude Haiku 4.5 has enough public results to be ranked (#165); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. Claude Haiku 4.5 scores higher in 1 category and DeepSeek-V2 (MoE-236B, May 2024) in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Claude Haiku 4.5 leads 44.0 to 40.4.
- DeepSeek-V2 (MoE-236B, May 2024) has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | DeepSeek-V2 (MoE-236B, May 2024) | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 39.5 | 40.3 |
| Released | 2025-10-15 | 2024-05-07 |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 53 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.0 (#78), DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139)
| Benchmark | Claude Haiku 4.5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| BigCodeBench Instruct | — | 48.9% |
| LMArena Coding | 1453 | — |
| BigCodeBench Complete | — | 59.4% |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.6 (#52), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude Haiku 4.5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning Not comparable
Claude Haiku 4.5: 15.1 (#320), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude Haiku 4.5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| Epoch Capabilities Index | 142.41 | 124.77 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| LMArena Hard Prompts | 1420 | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| BIG-Bench Hard | — | 78.8% |
| ForecastBench | 61.4 | — |
| HellaSwag | — | 87.1% |
| PIQA | — | 83.9% |
| WinoGrande | — | 86.3% |
Math Not comparable
Claude Haiku 4.5: 44.9 (#78), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude Haiku 4.5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| LMArena Math | 1396 | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Not comparable
Claude Haiku 4.5: 37.7 (#153), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude Haiku 4.5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
| LMArena Expert | 1442 | — |
| ARC (AI2) Challenge | — | 92.2% |
| MMLU | — | 78.4% |
| TriviaQA | — | 80% |
Multimodal Not comparable
Claude Haiku 4.5: 26.8 (#118), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude Haiku 4.5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Not comparable
Claude Haiku 4.5: 49.9 (#129), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude Haiku 4.5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Non-English | 1377 | — |
| LMArena Chinese | 1417 | — |
| LMArena French | 1408 | — |
| LMArena German | 1375 | — |
| LMArena Japanese | 1339 | — |
| LMArena Korean | 1347 | — |
| LMArena Russian | 1381 | — |
| LMArena Spanish | 1420 | — |
Instruction Following Not comparable
Claude Haiku 4.5: 71.4 (#149), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude Haiku 4.5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| IFEval | 80.1% | — |
| LMArena Instruction Following | 1414 | — |
Long Context Not comparable
Claude Haiku 4.5: 43.6 (#92), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude Haiku 4.5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Longer Query | 1427 | — |
Writing & Preference Not comparable
Claude Haiku 4.5: 57.9 (#123), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude Haiku 4.5 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Text | 1396 | — |
| LMArena Creative Writing | 1372 | — |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
| LMArena Multi-Turn | 1409 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than DeepSeek-V2 (MoE-236B, May 2024)?
Claude Haiku 4.5 has enough public results to be ranked (#165); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is Claude Haiku 4.5 or DeepSeek-V2 (MoE-236B, May 2024) better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 40.4 in the Noometry coding category.
How many benchmarks do Claude Haiku 4.5 and DeepSeek-V2 (MoE-236B, May 2024) share?
1 benchmark has published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and DeepSeek-V2 (MoE-236B, May 2024) has 10.