Recent studyBlind TTS Elo is live. Compare two anonymous voice samples, vote after listening, and help separate real preference signal from noise.Vote in the study ->
Codesota · Models · Qwen3-Coder-NextQwen8 results · 7 benchmarks
Model card

Qwen3-Coder-Next.

QwenLarge language model

Added from Papers with Code MMLU-Pro refresh on 2026-05-19.

§ 02 · Benchmarks

Every benchmark Qwen3-Coder-Next has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01AIME 2024Reasoning · Mathematical Reasoningaccuracy89.0%#5/11source ↗
02AIME 2025Reasoning · Mathematical Reasoningaccuracy83.1%#14/22source ↗
03SWE-Bench VerifiedComputer Code · Code Generationaccuracy70.6%#16/22source ↗
04LiveCodeBenchComputer Code · Code Generationpass-158.9%#20/24source ↗
05MMLUReasoning · Commonsense Reasoningaccuracy87.7%#29/64source ↗
06GPQA DiamondReasoning · Multi-step Reasoningaccuracy74.5%#41/74source ↗
07MMLU-ProReasoning · Commonsense Reasoningaccuracy80.5%#45/732026-02-28source ↗
08MMLU-ProReasoning · Commonsense Reasoningaccuracy80.5%#45/73source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where Qwen3-Coder-Next actually performs.

Computer Code
2
benchmarks
avg rank #18.0
Reasoning
5
benchmarks
avg rank #29.8
§ 04 · Papers

1 paper with results for Qwen3-Coder-Next.

  1. 2026-02-28· 7 results

    Qwen3-Coder-Next Technical Report

§ 05 · Related models

Other Qwen models scored on Codesota.

Qwen3-VL-235B-A22B-Instruct
9 results · 1 SOTA
Qwen3-VL-235B-A22B-Thinking
9 results
Qwen3-VL-8B-Instruct
9 results
Qwen2.5-Plus
1 result
Qwen2.5-VL-72B
1 result
Qwen3-235B-A22B (Base)
1 result
Qwen3.5-122B-A10B
1 result
Qwen3.5-27B
1 result
§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
7
results
paperswithcode
1
result
0 of 8 rows marked verified.