Qwen3 Coder 480B A35B Instruct
Qwen3 Coder 480B A35B Instruct is behind the leaders in factuality, agentic tasks, and coding. Too few results yet to rate reasoning, safety, long context, math, multimodal tasks, multilingual tasks, or instruction following.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Reasoning, Safety, Long Context, Math, Multimodal, Multilingual or Instruction Following.
Price
$1.50input$7.50outputper million tokens
From Alibaba's own price page · 4 providers tracked · All prices
Evidence
34results on28benchmarks
- 6 independently verified
- 15 aggregator
- 8 vendor-reported
- 5 cross-referenced
From 7 sources · latest Oct 8, 2026 · How verification works
Qwen3 Coder 480B A35B Instruct benchmark results
34 results on 28 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
34.2% behind the leader2 of 4 ranked benchmarks measured
- AA-Omniscience · Non-hallucination55.07Oct 8, 2026omniscienceNonHallucination
- AA-Omniscience · Accuracy15.68Oct 8, 2026omniscienceAccuracy
43.7% behind the leader1 of 7 ranked benchmarks measured
- 0.22Jun 15, 2026
45.3% behind the leader6 of 10 ranked benchmarks measured
- 69.60Oct 7, 2026
- 54.70Oct 7, 2026
- SciCode35.88Sep 4, 2026aa_scicode
- 38.70Oct 8, 2026
- 1273.25May 22, 2026
- Terminal-Bench Hard18.94Oct 8, 2026aa_terminalbench_hard
Show 4 more coding resultsHide 4 coding results
- 1281.66Jun 19, 2026
- 54.70May 15, 2026
- 55.40May 1, 2026
- 69.60May 15, 2026
0 of 6 ranked benchmarks measured
- 0.00Oct 8, 2026
- GPQA Diamond61.82Oct 8, 2026gpqa
- Humanity's Last Exam4.54Oct 8, 2026aa_hle
0 of 3 ranked benchmarks measured
- 45.67Oct 8, 2026
0 of 3 ranked benchmarks measured
- IFBench40.48Oct 8, 2026aa_ifbench
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- AA Intelligence12.00Aug 6, 2026Artificial Analysis Intelligence Index
- 55.40Jun 19, 2026
- τ²-Bench Telecom (AA run)43.57Oct 8, 2026aa_tau2
- AA Intelligence11.90Oct 8, 2026aa_intelligence_index
- -22.20Oct 8, 2026
- 18.31Jun 18, 2026
Show 10 more resultsHide 10 results
- 61.80Oct 7, 2026
- 24.59Jun 18, 2026
- 68.70Oct 7, 2026
- 25.80Oct 7, 2026
- 32.70May 15, 2026
- 64.70May 15, 2026
- TAU-bench (airline)60.00Oct 7, 2026TAU-bench Airline
- TAU-bench (retail)77.50Oct 7, 2026TAU-bench Retail
- 37.50May 15, 2026
- 37.50Oct 7, 2026
Qwen3 Coder 480B A35B Instruct: common questions
Who makes Qwen3 Coder 480B A35B Instruct?
Qwen3 Coder 480B A35B Instruct is made by Alibaba.
When was Qwen3 Coder 480B A35B Instruct released?
Qwen3 Coder 480B A35B Instruct was released on Jul 22, 2025, according to Artificial Analysis.
What is Qwen3 Coder 480B A35B Instruct good at?
Qwen3 Coder 480B A35B Instruct is behind the leaders in factuality, agentic tasks, and coding. Too few results yet to rate reasoning, safety, long context, math, multimodal tasks, multilingual tasks, or instruction following.
How much does Qwen3 Coder 480B A35B Instruct cost?
Qwen3 Coder 480B A35B Instruct costs $1.50 per million input tokens and $7.50 per million output tokens, according to Alibaba's own price page. We track its price at 4 providers. At a mix of three input tokens to one output token, it costs more than 75% of the 330 priced models we track.
How many benchmarks has Qwen3 Coder 480B A35B Instruct been tested on?
We track 34 results for Qwen3 Coder 480B A35B Instruct on 28 benchmarks from 7 sources, 6 of them independently verified. The latest was recorded on Oct 8, 2026.
About this record
Where Qwen3 Coder 480B A35B Instruct's numbers come from, and every name it appears under.
- Tracked since
- Apr 25, 2026
- Newest source mention
- Sep 11, 2026
Where the results come from
Verification: 34 scores · 6 independently verified · 15 aggregator-attributed · 5 vendor cross-reference · 8 vendor-reported. How these tiers are assigned
From 7 sources on 6 sites. Artificial Analysis supplies 16 of them; the 6 independently verified results come from 4 sites. Bars are coloured by trust tier.
- artificialanalysis.ai16
- api.llm-stats.com8
- huggingface.co5
- datasets-server.huggingface.co2
- swebench.com2
- labs.scale.com1