Undominated.ai

Alternatives to Qwen3.5-122B-A10B

Qwen LMArena 1417.1 $0.715/M on a balanced workload prices as of 2026-10-06

9 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, 26 score at least as high as Qwen3.5-122B-A10B and cost no more under at least one listed workload, with at least one of those dimensions improved. 9 match or beat its recorded context, maximum output, input modes, tool use and extended reasoning. 17 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

WorkloadQwen3.5-122B-A10B $/MRecorded capabilities preservedRecorded capability losses
Balanced$0.715714
Summarise$0.351815
Chat$0.988816
Code gen$1.35816
Agentic$0.533816

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

Intelligence1417.1
Context window262K
Max output65K
Input modestext, image, video
Tool useyes
Extended reasoningyes

Preserving recorded capabilities requires matching or beating these fields. Full record for Qwen3.5-122B-A10B, or check Qwen3.5-122B-A10B against the whole catalogue.

Recorded capabilities preserved 9

Each option has a higher score or a lower price, with neither dimension worse under the listed workloads. It matches or beats Qwen3.5-122B-A10B on recorded context, maximum output, input modes, tool use and extended reasoning.

#ModelIntelligence$/MHolds under
1MiMo-V2.6-Pro Xiaomi1491 +73.9$0.540
  • Balanced −24%
  • Summarise −6%
  • Chat −52%
  • Code gen −51%
  • Agentic −55%
2GLM 5.3 Flash Z.ai1469.6 +52.5$0.238
  • Balanced −67%
  • Summarise −62%
  • Chat −74%
  • Code gen −74%
  • Agentic −75%
3MiMo-V2.6-Flash Xiaomi1456.4 +39.3$0.175
  • Balanced −76%
  • Summarise −69%
  • Chat −84%
  • Code gen −84%
  • Agentic −85%
4Qwen3.8 27B Qwen1440.7 +23.6$0.562
  • Balanced −21%
  • Summarise −48%
  • Chat −15%
  • Code gen −10%
  • Agentic −31%
5Gemma 4 26B A4B Google1433.9 +16.8$0.127
  • Balanced −82%
  • Summarise −80%
  • Chat −85%
  • Code gen −85%
  • Agentic −85%
6MiniMax M3 MiniMax1432.1 +15$0.485
  • Balanced −32%
  • Summarise −27%
  • Chat −45%
  • Code gen −44%
  • Agentic −49%
7MiMo-V2.5 Xiaomi1427.5 tie$0.175
  • Balanced −76%
  • Summarise −69%
  • Chat −84%
  • Code gen −84%
  • Agentic −85%
8Qwen3.6 Plus Qwen1436.7 +19.6$0.975 chat
  • Chat −1%
  • Code gen −4%
9Gemini 3.5 Flash Lite Google1434.7 +17.6$0.333 summarise
  • Summarise −5%
  • Agentic −12%

Alternatives with recorded capability losses 17

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 V4.1 Flash DeepSeek1462.5 +45.4$0.182
  • Balanced −75%
  • Summarise −81%
  • Chat −75%
  • Code gen −73%
  • Agentic −80%
  • no video input
MiMo-V2.5-Pro Xiaomi1465 +47.9$0.544
  • Balanced −24%
  • Summarise −5%
  • Chat −51%
  • Code gen −51%
  • Agentic −54%
  • no image, video input
Qwen3.7 Plus Qwen1454.6 +37.5$0.560
  • Balanced −22%
  • Summarise −16%
  • Chat −37%
  • Code gen −35%
  • Agentic −42%
  • no video input
Gemma 4 31B Google1443.4 +26.3$0.205
  • Balanced −71%
  • Summarise −56%
  • Chat −75%
  • Code gen −78%
  • Agentic −66%
  • 66K → 16K max output
Hy3 Tencent1440.7 +23.6$0.231
  • Balanced −68%
  • Summarise −65%
  • Chat −74%
  • Code gen −73%
  • Agentic −75%
  • no image, video input
DeepSeek V4 Flash 0423 DeepSeek1432.1 +15$0.113
  • Balanced −84%
  • Summarise −79%
  • Chat −89%
  • Code gen −90%
  • Agentic −89%
  • no image, video input
GPT-5.6 Luna OpenAI1431 +13.9$0.450
  • Balanced −37%
  • Summarise −43%
  • Chat −45%
  • Code gen −42%
  • Agentic −54%
  • no video input
DeepSeek V3.2 DeepSeek1424.5 tie$0.290
  • Balanced −59%
  • Summarise −35%
  • Chat −73%
  • Code gen −76%
  • Agentic −62%
  • 262K → 164K context
  • no image, video input
DeepSeek V3.2 Exp DeepSeek1422.4 tie$0.305
  • Balanced −57%
  • Summarise −21%
  • Chat −67%
  • Code gen −74%
  • Agentic −45%
  • 262K → 164K context
  • no image, video input
Qwen3 235B A22B Instruct 2507 Qwen1419.3 tie$0.205
  • Balanced −71%
  • Summarise −68%
  • Chat −72%
  • Code gen −73%
  • Agentic −70%
  • 66K → 16K max output
  • no image, video input
  • no extended reasoning
Qwen3 VL 235B A22B Instruct Qwen1420.1 tie$0.370
  • Balanced −48%
  • Summarise −41%
  • Chat −55%
  • Code gen −56%
  • Agentic −53%
  • 66K → 33K max output
  • no video input
  • no extended reasoning
Qwen3 Next 80B A3B Instruct Qwen1417.3 tie$0.268
  • Balanced −63%
  • Summarise −63%
  • Chat −63%
  • Code gen −63%
  • Agentic −63%
  • no image, video input
  • no extended reasoning
DeepSeek V3.1 DeepSeek1419.7 tie$0.453
  • Balanced −37%
  • Summarise −13%
  • Chat −43%
  • Code gen −48%
  • Agentic −29%
  • 262K → 164K context
  • 66K → 33K max output
  • no image, video input
DeepSeek V3.1 Terminus DeepSeek1417.1 tie$0.453
  • Balanced −37%
  • Summarise −13%
  • Chat −43%
  • Code gen −48%
  • Agentic −29%
  • 262K → 164K context
  • no image, video input
GLM 5.3 Z.ai1471.4 +54.3$0.346 summarise
  • Summarise −1%
  • no image, video input
GLM 4.6 Z.ai1439.9 +22.8$0.853 chat
  • Chat −14%
  • Code gen −12%
  • Agentic −21%
  • 262K → 205K context
  • 66K → 16K max output
  • no image, video input
GLM 4.7 Z.ai1435.5 +18.4$0.844 chat
  • Chat −15%
  • Code gen −12%
  • Agentic −23%
  • 262K → 205K context
  • no image, video input

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