--- title: "Is DeepSeek V3 still undominated? · Undominated.ai" canonical: https://undominated.ai/check/deepseek__deepseek-chat/ description: "DeepSeek V3: 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 DeepSeek V3 still undominated? · Undominated.ai > DeepSeek V3: 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 DeepSeek V3 a good deal? Whether anything in this catalogue beats DeepSeek V3 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, DeepSeek V3 is dominated for Balanced on LMArena. GLM 5.3 Flash scores 139.5 higher and costs 49% less, with a covering envelope. 13 of 136 rated, priced standard models are undominated. [Inspect model evidence](/models/deepseek__deepseek-chat/) [Compare differences & requirements](/compare/?models=deepseek%2Fdeepseek-chat%2Cz-ai%2Fglm-5.3-flash) Current model DeepSeek V3 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) GLM 5.3 Flash is both better and cheaper than DeepSeek V3: 139.5 points higher on LMArena and 49% less per million tokens, $0.23 cheaper at this mix. [DeepSeek V3](https://undominated.ai/models/deepseek__deepseek-chat/) LMArena Elo · higher is better Scale starts at 1040 Elo ** 1332.4 Effective $/M · Balanced · lower is better ** $0.463/M [GLM 5.3 Flash](https://undominated.ai/models/z-ai__glm-5.3-flash/) LMArena Elo · higher is better Scale starts at 1040 Elo ** 1471.9 Effective $/M · Balanced · lower is better ** $0.237/M DeepSeek V3 takes text, returns up to 16,384 tokens from a 163,840-token context, and is listed by 2 sellers. Compared against 136 rated, priced models on this lens: 23 models dominate it and give up nothing, 5 more dominate it but give something up. DeepSeek V3 scores 1332.4 at $0.46 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 | | --- | --- | --- | --- | | [GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) | 1471.9 +139.5 | $0.237/M | 49% | | [Gemma 4 31B](/models/google__gemma-4-31b-it/) | 1441.7 +109.3 | $0.153/M | 67% | | [Hy3](/models/tencent__hy3/) | 1440.6 +108.2 | $0.144/M | 69% | | [Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) | 1434.5 +102.1 | $0.143/M | 69% | | [DeepSeek V4 Flash 0423](/models/deepseek__deepseek-v4-flash/) | 1431.8 +99.4 | $0.103/M | 78% | | [GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) | 1429.9 +97.5 | $0.450/M | 3% | | [MiMo-V2.5](/models/xiaomi__mimo-v2.5/) | 1427.4 +95.0 | $0.175/M | 62% | | [DeepSeek V3.2](/models/deepseek__deepseek-v3.2/) | 1424.8 +92.4 | $0.302/M | 35% | | [DeepSeek V3.2 Exp](/models/deepseek__deepseek-v3.2-exp/) | 1422.6 +90.2 | $0.305/M | 34% | | [Qwen3 235B A22B Instruct 2507](/models/qwen__qwen3-235b-a22b-2507/) | 1419.8 +87.4 | $0.153/M | 67% | | [DeepSeek V3.1](/models/deepseek__deepseek-chat-v3.1/) | 1419.7 +87.3 | $0.425/M | 8% | | [Qwen3 Next 80B A3B Instruct](/models/qwen__qwen3-next-80b-a3b-instruct/) | 1417.6 +85.2 | $0.343/M | 26% | | [DeepSeek V3.1 Terminus](/models/deepseek__deepseek-v3.1-terminus/) | 1416.9 +84.5 | $0.453/M | 2% | | [Step 3.5 Flash](/models/stepfun__step-3.5-flash/) | 1403.7 +71.3 | $0.150/M | 68% | | [Qwen3.5-Flash](/models/qwen__qwen3.5-flash-02-23/) | 1397.7 +65.3 | $0.114/M | 75% | | [Qwen3 30B A3B Instruct 2507](/models/qwen__qwen3-30b-a3b-instruct-2507/) | 1383.6 +51.2 | $0.084/M | 82% | | [Solar Pro 4](/models/upstage__solar-pro4/) | 1377.3 +44.9 | $0.158/M | 66% | | [DeepSeek V3 0324](/models/deepseek__deepseek-chat-v3-0324/) | 1375.0 +42.6 | $0.438/M | 5% | | [GPT-5.4 Nano](/models/openai__gpt-5.4-nano/) | 1372.9 +40.5 | $0.463/M | 0% | | [Qwen3 Next 80B A3B Thinking](/models/qwen__qwen3-next-80b-a3b-thinking/) | 1367.8 +35.4 | $0.412/M | 11% | | [GLM 4.7 Flash](/models/z-ai__glm-4.7-flash/) | 1352.2 +19.8 | $0.145/M | 69% | | [MiniMax M2](/models/minimax__minimax-m2/) | 1342.1 +9.7 | $0.446/M | 4% | | [Trinity Large Thinking](/models/arcee-ai__trinity-large-thinking/) | 1341.8 +9.4 | $0.388/M | 16% | ## 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 | | --- | --- | --- | --- | | [GLM 4.5 Air](/models/z-ai__glm-4.5-air/) | 1383.7 | $0.310/M | context | | [GLM 4.6V](/models/z-ai__glm-4.6v/) | 1376.5 | $0.450/M | context | | [gpt-oss-120b](/models/openai__gpt-oss-120b/) | 1365.9 | $0.262/M | context | | [Gemma 3 27B](/models/google__gemma-3-27b-it/) | 1357.7 | $0.172/M | context | | [Mercury 2](/models/inception__mercury-2/) | 1357.6 | $0.375/M | context | 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/)