qwen3-coder-next

qwen3-coder-next ranks first on 3 of the 26 benchmarks it has scores on.

Qwen Released 2 Feb 2026 Family Qwen3-Coder The lab's model card

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Qwen Feb 2026

Open weights Small

No Epoch Capabilities Index score yet

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Benchmark	Score	Rank	Source
MMLU	87.7%	#29 of 127	Model card
MMLU-Pro	80.5%	#73 of 151	Model card
MMLU-Redux	91.2%	#19 of 38	Model card
SuperGPQA	57.5%	#19 of 26	Model card

Benchmark	Score	Rank	Source
AIME 2024	89%	#22 of 87	Model card
GPQA Diamond	74.5%	#142 of 284	Model card
AIME 2025	83.1%	#81 of 143	Model card
HMMT 2025	70.2%	#43 of 49	Model card
CritPt	0%	#151 of 160	Epoch AI
HMMT Nov 2025	75.6%	#22 of 23	Model card

Benchmark	Score	Rank	Source
MultiPL-E	88.2%	#1 of 18	Model card
Bird-SQL	63.6%	#1 of 13	Model card
CRUXEval	95.9%	#1 of 9	Model card
Spider	83.7%	#1 of 4	Model card
EvalPlus	86.6%	#2 of 6	Model card
Aider Polyglot	66.2%	#12 of 29	Model card
Codeforces rating	2,100	#19 of 41	Model card
SWE-bench Verified	70.6%	#72 of 150	Model card
OpenHands Index	43.8%	#24 of 33	Official leaderboard
SWE-bench Multilingual	62.8%	#55 of 70	Model card
FullStackBench	60.6%	#5 of 6	Model card
WeirdML	34.4%	#95 of 112	Official leaderboard
LiveCodeBench v6	58.9%	#66 of 76	Model card
SWE-Bench Pro	44.3%	#74 of 77	Model card
OJBench	23%	#12 of 12	Model card

Benchmark	Score	Rank	Source
SnakeBench	21	#119 of 183	Official leaderboard
Terminal-Bench 2.0	36.2%	#53 of 61	Model card
Template Following generalization (Qwen)	92.7%	#1 of 1	Model card

Benchmark	Score		Rank	Source
PrimeVul	48.3%		#2 of 2	Model card
CWEval	56.3%		#1 of 1	Model card

The benchmarks the lab chose to headline, with the scores it gave.

Every result in the longer documents the lab published with it. 23 of them aren't in the launch post.