The Open-Source AI Stack
RSS
All models

Models · Compare

DeepSeek-V2.5 vs Claude 3.5 Haiku

Rows highlighted in warm gray are where the models differ. Numbers carry their as-of date and primary source.

Specs

Field A: DeepSeek-V2.5 B: Claude 3.5 Haiku
Released 2024-11-04
Developer DeepSeekAnthropic
Openness Open weightsProprietary
License DeepSeek LicenseProprietary
OSI-approved nono
Data released nono
Training code nono
Architecture moeunknown
Total params
Active params
Experts
Context window 200K
Attention mlaunknown
Position enc. rope-yarnunknown
Pretraining tokens
Post-training sft, rlhfrlhf, constitutional
Training hardware
$/M input $0.00$0.80
$/M output $0.00$4.00
Output tok/sec 00

Benchmarks

Missing scores render as not reported; never inferred. Bold highlights the leader per benchmark.

General reasoning

MMLU-Pro 63.4 2026-05-21
GPQA-Diamond 40.8 2026-05-21

Code

HumanEval 89.0 2024-09-05
SWE-Bench Verified 40.6 2024-10-22
LiveCodeBench 41.8 2024-09-05 31.4 2026-05-21

Math

MATH 72.1 2026-05-21
AIME 2024 3.3 2026-05-21

Context · A

Intermediate checkpoint between DeepSeek-V2 and DeepSeek-V3. Merged the previously separate Chat (V2-0628) and Coder (Coder-V2-0724) tracks into a single model, reusing the V2 architecture (236B MoE, 21B active, MLA, 128K context) and adding function calling, JSON mode, and FIM completion.

Context · B

Announced October 22 2024 alongside the upgraded Claude 3.5 Sonnet and the computer-use beta; generally available in early November. Anthropic positioned it as matching Claude 3 Opus on many intelligence benchmarks at Haiku-tier speeds, with a SWE-Bench Verified score of 40.6% making it briefly the best small-tier coding model from a major lab.

DeepSeek-V2.5 detail → · Claude 3.5 Haiku detail →