readable AI benchmarks

Alibaba

Qwen3 Coder Next

non-reasoning · open weights · Feb 3, 2026

Quality Score18.2
Value Score18.8
Reliability18.8
Cache Discount0%

Model specification

Reasoning
non-reasoning
Input modalities
text
Output modalities
text
Context window
256k tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.350
Output
$1.20
Cached Input
$0.350
Cached Output
not available
Cost per task
$0.337

Capability

Intelligence
21.3
Coding
36.2
Agentic
8.9
Omniscience
-62.4
Correct
16.2%
Blended price
$0.435

Answer outcomes

Correct 16.2%Incorrect 78.5%Abstained 5.3%

Artificial Analysis benchmarks

GDPval-AA v2
11%
τ³-Banking
5%
Terminal-Bench v2.1
38%
SciCode
32%
Humanity’s Last Exam
10%
GPQA Diamond
74%
CritPt
0%
AA-Omniscience
19%
AA-LCR
42%

Similar models