Claude 3.5 HaikuvsQwen3-Coder-Next

Claude 3.5 Haiku
Qwen3-Coder-Next
Specifications
Parameters
80B
Context window
256k
API pricing
Input price
$0.30
Output price
$1.50
Benchmarks
SWE-Bench Verified
40.6%70.6%
Benchmarks
BullshitBench v2
50%
SWE-Bench Pro
44.3%
SWE-Bench Multilingual
62.8%
Terminal-Bench 2.0
36.2%
GPQA Diamond
41.6%
Overview
CompanyAnthropicQwen
Release dateOct 22 2024Feb 3 2026
AccessProprietaryOpen Weight

Frequently asked questions

Qwen3-Coder-Next leads Claude 3.5 Haiku on 1 of the 1 benchmark they both report (SWE-Bench Verified). Only Qwen3-Coder-Next has a verified first-party API price: $0.30 per million input tokens and $1.50 per million output tokens. No pay-as-you-go API rate is tracked for Claude 3.5 Haiku. Claude 3.5 Haiku shipped 469 days before Qwen3-Coder-Next, so benchmark comparisons should account for the intervening progress.

Claude 3.5 Haiku is proprietary, while Qwen3-Coder-Next is open weight.

On SWE-Bench Verified, Qwen3-Coder-Next leads at 70.6% vs Claude 3.5 Haiku at 40.6%.

Claude 3.5 Haiku was released by Anthropic on Oct 22 2024.

Qwen3-Coder-Next was released by Qwen on Feb 3 2026.

Qwen3-Coder-Next leads on SWE-Bench Verified — Claude 3.5 Haiku 40.6% vs Qwen3-Coder-Next 70.6%.

Only Qwen3-Coder-Next has a verified first-party API price: $0.30 per million input tokens and $1.50 per million output tokens. No pay-as-you-go API rate is tracked for Claude 3.5 Haiku. Rates are pay-as-you-go API prices verified on August 18, 2026.

Claude 3.5 Haiku is a proprietary model released by Anthropic. Qwen3-Coder-Next is an open weight model released by Qwen.

Other comparisons