NEWMEN
← back to all models

Qwen: Qwen3 235B A22B

qwen/qwen3-235b-a22b

Alibaba (Qwen)open-weight131K context1 providerIntelligence 73.4

Cheapest provider

$0.46 / 1M

Alibaba

Fastest provider (p95)

No throughput data yet — populated as traffic accumulates

Intelligence (composite)

73.4

MMLU-Pro · HumanEval · math · GPQA

Per-provider performance

Latency / throughput / uptime measured across providers over the last 30 minutes of live traffic. Atlas’s router weighs these per call (with the eval-gate signal) when picking a variant for Standard and Batch tiers.

ProviderQuantInput $/1MOutput $/1MLatency p50 / p95Throughput p50 / p95Uptime 30mSuccess
Alibabaundisclosed$0.4550$1.8200100.00%

“—” means live telemetry hasn’t accumulated enough recent traffic for that endpoint. “undisclosed” means the provider serves the model but doesn’t expose the quantization label (typically running fp8 / int8 internally).

Intelligence breakdown

Composite score is a weighted average of public benchmarks (30% MMLU-Pro, 25% code pass@1, 25% math, 20% GPQA). Numbers come from model cards and the Artificial Analysis intelligence harness; missing components are renormalised over what’s present.

MMLU-Pro

82.8

broad reasoning

Code

55.7

pass@1 (HumanEval / LiveCodeBench)

AIME 2025

81.5

math accuracy

GPQA Diamond

71.1

hard reasoning

Source: Qwen3-235B-A22B (thinking) model card (MMLU-Pro 82.8, GPQA 71.1, LiveCodeBench 55.7, AIME25 81.5); huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507

How Atlas routes Qwen: Qwen3 235B A22B

  • Realtime tier — direct passthrough at the upstream’s native precision. Best for hard latency / quality guarantees.
  • Standard tier — Atlas picks the cheapest provider variant whose quantization has stayed green on your operation’s eval gates. For Qwen: Qwen3 235B A22B that’s currently Alibaba at $0.46/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.