--- title: "Is Qwen3 30B A3B still undominated? · Undominated.ai" canonical: https://undominated.ai/check/qwen__qwen3-30b-a3b/ description: "Qwen3 30B A3B: whether it is still undominated. If anything in this catalogue is both better and cheaper, it is named, as of Sep 23, 2026. Unrated stays unrated." --- # Is Qwen3 30B A3B still undominated? · Undominated.ai > Qwen3 30B A3B: whether it is still undominated. If anything in this catalogue is both better and cheaper, it is named, as of Sep 23, 2026. Unrated stays unrated. # Is Qwen3 30B A3B a good deal? Whether anything in this catalogue beats Qwen3 30B A3B on both quality and price, and what you give up if it does. A computation on the current catalogue, not an opinion. 13 undominated of 136 · Sep 23, 2026 [1 · Choose & set workload](#check-input)[2 · Read verdict](#check-verdict)[3 · Inspect alternatives](#check-options) As of Sep 23, 2026, Qwen3 30B A3B is dominated for Balanced on LMArena. Gemma 4 31B scores 124.7 higher and costs 29% less, with a covering envelope. 13 of 136 rated, priced standard models are undominated. [Inspect model evidence](/models/qwen__qwen3-30b-a3b/) [Compare differences & requirements](/compare/?models=qwen%2Fqwen3-30b-a3b%2Cgoogle%2Fgemma-4-31b-it) Current model Qwen3 30B A3B Balanced 3 tokens in per 1 out Balanced Summarise Chat Code gen Agentic Monthly spend (USD) Used only to say how many months a named switching cost would take to earn back. Leave blank to skip. Switching cost (USD) Gemma 4 31B is both better and cheaper than Qwen3 30B A3B: 124.7 points higher on LMArena and 29% less per million tokens, $0.06 cheaper at this mix. [Qwen3 30B A3B](https://undominated.ai/models/qwen__qwen3-30b-a3b/) LMArena Elo · higher is better Scale starts at 1040 Elo ** 1317.0 Effective $/M · Balanced · lower is better ** $0.215/M [Gemma 4 31B](https://undominated.ai/models/google__gemma-4-31b-it/) LMArena Elo · higher is better Scale starts at 1040 Elo ** 1441.7 Effective $/M · Balanced · lower is better ** $0.153/M Qwen3 30B A3B takes text, returns up to 16,384 tokens from a 131,072-token context, and is listed by 2 sellers. Compared against 136 rated, priced models on this lens: 11 models dominate it and give up nothing, 4 more dominate it but give something up. Qwen3 30B A3B scores 1317 at $0.21 per million tokens for this mix. ## Envelope-safe replacements Each row scores at least as high, costs no more, and covers this model’s context, output, modalities, tools, and reasoning. A cheaper narrower model is not listed here. | Model | LMArena | Effective $/M | You save | | --- | --- | --- | --- | | [Gemma 4 31B](/models/google__gemma-4-31b-it/) | 1441.7 +124.7 | $0.153/M | 29% | | [Hy3](/models/tencent__hy3/) | 1440.6 +123.6 | $0.144/M | 33% | | [Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) | 1434.5 +117.5 | $0.143/M | 34% | | [DeepSeek V4 Flash 0423](/models/deepseek__deepseek-v4-flash/) | 1431.8 +114.8 | $0.103/M | 52% | | [MiMo-V2.5](/models/xiaomi__mimo-v2.5/) | 1427.4 +110.4 | $0.175/M | 19% | | [Step 3.5 Flash](/models/stepfun__step-3.5-flash/) | 1403.7 +86.7 | $0.150/M | 30% | | [Qwen3.5-Flash](/models/qwen__qwen3.5-flash-02-23/) | 1397.7 +80.7 | $0.114/M | 47% | | [Solar Pro 4](/models/upstage__solar-pro4/) | 1377.3 +60.3 | $0.158/M | 27% | | [GLM 4.7 Flash](/models/z-ai__glm-4.7-flash/) | 1352.2 +35.2 | $0.145/M | 32% | | [Qwen3 32B](/models/qwen__qwen3-32b/) | 1340.0 +23.0 | $0.130/M | 40% | | [GPT-5 Nano](/models/openai__gpt-5-nano/) | 1319.7 +2.7 | $0.138/M | 36% | ## Higher score, lower price, named losses Not a drop-in. The loss is why these are not a recommendation. | Model | LMArena | Effective $/M | You give up | | --- | --- | --- | --- | | [Qwen3 235B A22B Instruct 2507](/models/qwen__qwen3-235b-a22b-2507/) | 1419.8 | $0.153/M | reasoning | | [Qwen3 30B A3B Instruct 2507](/models/qwen__qwen3-30b-a3b-instruct-2507/) | 1383.6 | $0.084/M | reasoning | | [Gemma 3 27B](/models/google__gemma-3-27b-it/) | 1357.7 | $0.172/M | reasoning | | [Gemma 3 12B](/models/google__gemma-3-12b-it/) | 1334.2 | $0.075/M | reasoning | 136 rated, priced standard models. Chartreuse is the frontier. Cobalt is the model you named, when it is not on the staircase. Copy watch URL [Open the frontier](/frontier/) The link keeps the model and mix, using the current catalogue. Monthly spend and switching cost stay in this browser tab and are left out of the link. ## Saved decision references Save the model, workload, catalogue date and capability-preservation rule in this browser. Spend, switching cost and bill contents are not saved. No account or notifications. Constraint: replacements must preserve the model’s capabilities; any losses remain named trade-offs. Historical decisions cannot be fully replayed from saved references: past prices, scores and capability evidence are not stored. Save this reference ## Continue your investigation - [Build a shortlist](/compare/) - [Inspect alternatives](/alternatives/) - [Check billing conditions](/traps/) - [Read model evidence](/models/)