Claude 3 HaikuvsQwen3.8-Max

Claude 3 Haiku
Qwen3.8-Max
Specifications
Parameters
2.4T
Context window
1M
API pricing
Cheapest input
$0.25Amazon Bedrock$2.00Alibaba
Cheapest output
$1.25Amazon Bedrock$6.00Alibaba
Benchmarks
BullshitBench v2
10%94%
Benchmarks
SWE-Bench Pro
67.7%
DeepSWE 1.1
56.6%
PaperBench
93%
NL2Repo-Bench
55.9%
QwenSWEBench V2
55.1%
Terminal-Bench 3.0
11.3%
Terminal-Bench 2.1
86.6%
JobBench
53.4%
CoWorkBench
74.8%
Toolathlon-Verified
72.5%
Humanity's Last Exam · with tools
43.6%
GPQA Diamond
33.3%
OSWorld-Verified
86.1%
CharXiv Reasoning
88.4%
BabyVision
82%
MMMU-Pro
82.3%
Overview
CompanyAnthropicQwen
Release dateMar 4 2024Aug 3 2026
AccessProprietaryProprietary

Other comparisons

Claude 3 HaikuvsGPT-6 AstraQwen3.8-MaxvsGPT-6 AstraClaude 3 HaikuvsGemini 3.8 FlashQwen3.8-MaxvsGemini 3.8 FlashClaude 3 HaikuvsMuse Spark 1.3Qwen3.8-MaxvsMuse Spark 1.3Claude 3 HaikuvsGrok 4.6Qwen3.8-MaxvsGrok 4.6Claude 3 HaikuvsDeepSeek-V4-Pro-0813Qwen3.8-MaxvsDeepSeek-V4-Pro-0813Claude 3 HaikuvsMistral Medium 3.5Qwen3.8-MaxvsMistral Medium 3.5

Frequently asked questions

Qwen3.8-Max leads Claude 3 Haiku on 1 of the 1 benchmark they both report (BullshitBench v2). Claude 3 Haiku shipped 882 days before Qwen3.8-Max, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On BullshitBench v2, Qwen3.8-Max leads at 94% vs Claude 3 Haiku at 10%.