Undominated.ai

Alternatives to Qwen3 235B A22B Instruct 2507

Qwen LMArena 1419.3 $0.205/M on a balanced workload prices as of 2026-10-06

8 models are higher-scoring or cheaper, with neither dimension worse.

Of the 144 models carrying both an independent score and a published price at the same delivery mode, 10 score at least as high as Qwen3 235B A22B Instruct 2507 and cost no more under at least one listed workload, with at least one of those dimensions improved. 8 match or beat its recorded context, maximum output, input modes, tool use and extended reasoning. 2 have a recorded capability loss, named on every row.

Dominance is not a property of a model. It is a property of a model, a capability lens and a workload, and all three are named on every row. Scores are LMArena Elo, used under CC BY 4.0 from the official dataset; prices are blended per million tokens. A higher score is not a drop-in replacement.

This page is built only while a candidate improves score or price without worsening the other under a listed workload. When that comparison no longer holds, it is not generated.

Where it holds

WorkloadQwen3 235B A22B Instruct 2507 $/MRecorded capabilities preservedRecorded capability losses
Balanced$0.20560
Summarise$0.11350
Chat$0.27481
Code gen$0.36682
Agentic$0.15970

Workload mixes are defined on the methodology page. Cached input is priced at the cached rate, and reasoning tokens at the worse of the reasoning and output rates.

What you would be replacing

Intelligence1419.3
Context window262K
Max output16K
Input modestext
Tool useyes
Extended reasoningno

Preserving recorded capabilities requires matching or beating these fields. Full record for Qwen3 235B A22B Instruct 2507, or check Qwen3 235B A22B Instruct 2507 against the whole catalogue.

Recorded capabilities preserved 8

Each option has a higher score or a lower price, with neither dimension worse under the listed workloads. It matches or beats Qwen3 235B A22B Instruct 2507 on recorded context, maximum output, input modes, tool use and extended reasoning.

#ModelIntelligence$/MHolds under
1DeepSeek V4.1 Flash DeepSeek1462.5 +43.2$0.182
  • Balanced −11%
  • Summarise −41%
  • Chat −10%
  • Code gen −2%
  • Agentic −34%
2MiMo-V2.6-Flash Xiaomi1456.4 +37.1$0.175
  • Balanced −15%
  • Summarise −5%
  • Chat −43%
  • Code gen −42%
  • Agentic −50%
3Gemma 4 31B Google1443.4 +24.1$0.205
  • Balanced same price
  • Chat −11%
  • Code gen −19%
4Gemma 4 26B A4B Google1433.9 +14.6$0.127
  • Balanced −38%
  • Summarise −39%
  • Chat −45%
  • Code gen −44%
  • Agentic −50%
5DeepSeek V4 Flash 0423 DeepSeek1432.1 +12.8$0.113
  • Balanced −45%
  • Summarise −35%
  • Chat −62%
  • Code gen −62%
  • Agentic −62%
6MiMo-V2.5 Xiaomi1427.5 tie$0.175
  • Balanced −15%
  • Summarise −5%
  • Chat −43%
  • Code gen −42%
  • Agentic −50%
7GLM 5.3 Flash Z.ai1469.6 +50.3$0.254 chat
  • Chat −7%
  • Code gen −4%
  • Agentic −18%
8Hy3 Tencent1440.7 +21.4$0.261 chat
  • Chat −5%
  • Code gen −1%
  • Agentic −17%

Alternatives with recorded capability losses 2

These improve score or price without worsening the other under the listed workloads, but reduce at least one recorded capability. Read the last column before switching.

ModelIntelligence$/MHolds underRecorded capability loss
DeepSeek V3.2 DeepSeek1424.5 tie$0.269 chat
  • Chat −2%
  • Code gen −12%
  • 262K → 164K context
DeepSeek V3.2 Exp DeepSeek1422.4 tie$0.354 code gen
  • Code gen −3%
  • 262K → 164K context

What this compares, and what it leaves out

  • Quality is LMArena Elo, used under CC BY 4.0 from the official dataset. The 95% confidence interval on a difference between two scores is about ±10.47 points, so a gap smaller than that is marked tie rather than an improvement — see significance bands.
  • 204 further models at this delivery mode carry a price but no independent score. They are absent from the comparison in both directions — unrated is not a zero, and an unmeasured model is neither an alternative nor a worse buy.
  • Retired models are never offered as an alternative, and a model only competes against its own delivery mode: batch trades latency for price, so it is not a like-for-like swap.
  • Nothing here measures latency, throughput, rate limits or how a model behaves on your prompts. Two models with the same index score are not interchangeable.
  • Models with no higher-scoring or cheaper alternative that is no worse on the other axis are on the value frontier. Models with such an alternative are listed here.
Evidence & Ask
Markdown for LLMs