--- title: "Is Gemma 2 27B still undominated? · Undominated.ai" canonical: https://undominated.ai/check/google__gemma-2-27b-it/ description: "Gemma 2 27B: 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 Gemma 2 27B still undominated? · Undominated.ai > Gemma 2 27B: 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 Gemma 2 27B a good deal? Whether anything in this catalogue beats Gemma 2 27B 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, Gemma 2 27B is dominated for Balanced on LMArena. GLM 5.3 Flash scores 240.6 higher and costs 63% less, with a covering envelope. 13 of 136 rated, priced standard models are undominated. [Inspect model evidence](/models/google__gemma-2-27b-it/) [Compare differences & requirements](/compare/?models=google%2Fgemma-2-27b-it%2Cz-ai%2Fglm-5.3-flash) Current model Gemma 2 27B 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 Gemma 2 27B: 240.6 points higher on LMArena and 63% less per million tokens, $0.41 cheaper at this mix. [Gemma 2 27B](https://undominated.ai/models/google__gemma-2-27b-it/) LMArena Elo · higher is better Scale starts at 1040 Elo ** 1231.3 Effective $/M · Balanced · lower is better ** $0.650/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 Gemma 2 27B takes text, returns up to 2,048 tokens from a 8,192-token context, and is listed by 1 seller. Compared against 136 rated, priced models on this lens: 52 models dominate it and give up nothing, none does so with a trade-off. Gemma 2 27B scores 1231.3 at $0.65 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 +240.6 | $0.237/M | 63% | | [MiMo-V2.5-Pro](/models/xiaomi__mimo-v2.5-pro/) | 1464.8 +233.5 | $0.544/M | 16% | | [Qwen3.7 Plus](/models/qwen__qwen3.7-plus/) | 1454.2 +222.9 | $0.560/M | 14% | | [Gemma 4 31B](/models/google__gemma-4-31b-it/) | 1441.7 +210.4 | $0.153/M | 77% | | [Hy3](/models/tencent__hy3/) | 1440.6 +209.3 | $0.144/M | 78% | | [Gemma 4 26B A4B](/models/google__gemma-4-26b-a4b-it/) | 1434.5 +203.2 | $0.143/M | 78% | | [MiniMax M3](/models/minimax__minimax-m3/) | 1433.5 +202.2 | $0.525/M | 19% | | [DeepSeek V4 Flash 0423](/models/deepseek__deepseek-v4-flash/) | 1431.8 +200.5 | $0.103/M | 84% | | [GPT-5.6 Luna](/models/openai__gpt-5.6-luna/) | 1429.9 +198.6 | $0.450/M | 31% | | [MiMo-V2.5](/models/xiaomi__mimo-v2.5/) | 1427.4 +196.1 | $0.175/M | 73% | | [DeepSeek V3.2](/models/deepseek__deepseek-v3.2/) | 1424.8 +193.5 | $0.302/M | 54% | | [DeepSeek V3.2 Exp](/models/deepseek__deepseek-v3.2-exp/) | 1422.6 +191.3 | $0.305/M | 53% | | [Qwen3 VL 235B A22B Instruct](/models/qwen__qwen3-vl-235b-a22b-instruct/) | 1420.6 +189.3 | $0.632/M | 3% | | [Qwen3 235B A22B Instruct 2507](/models/qwen__qwen3-235b-a22b-2507/) | 1419.8 +188.5 | $0.153/M | 76% | | [DeepSeek V3.1](/models/deepseek__deepseek-chat-v3.1/) | 1419.7 +188.4 | $0.425/M | 35% | | [Qwen3 Next 80B A3B Instruct](/models/qwen__qwen3-next-80b-a3b-instruct/) | 1417.6 +186.3 | $0.343/M | 47% | | [DeepSeek V3.1 Terminus](/models/deepseek__deepseek-v3.1-terminus/) | 1416.9 +185.6 | $0.453/M | 30% | | [Gemini 3.1 Flash Lite Preview](/models/google__gemini-3.1-flash-lite-preview/) | 1415.3 +184.0 | $0.563/M | 13% | | [Inkling Small](/models/thinkingmachines__inkling-small/) | 1412.3 +181.0 | $0.637/M | 2% | | [Qwen3.5-27B](/models/qwen__qwen3.5-27b/) | 1408.1 +176.8 | $0.536/M | 18% | | [MiniMax M2.7](/models/minimax__minimax-m2.7/) | 1404.6 +173.3 | $0.525/M | 19% | | [Step 3.5 Flash](/models/stepfun__step-3.5-flash/) | 1403.7 +172.4 | $0.150/M | 77% | | [Qwen3.5-Flash](/models/qwen__qwen3.5-flash-02-23/) | 1397.7 +166.4 | $0.114/M | 83% | | [Qwen3.5-35B-A3B](/models/qwen__qwen3.5-35b-a3b/) | 1395.5 +164.2 | $0.547/M | 16% | | [GLM 4.5 Air](/models/z-ai__glm-4.5-air/) | 1383.7 +152.4 | $0.310/M | 52% | | [Qwen3 30B A3B Instruct 2507](/models/qwen__qwen3-30b-a3b-instruct-2507/) | 1383.6 +152.3 | $0.084/M | 87% | | [Solar Pro 4](/models/upstage__solar-pro4/) | 1377.3 +146.0 | $0.158/M | 76% | | [GLM 4.6V](/models/z-ai__glm-4.6v/) | 1376.5 +145.2 | $0.450/M | 31% | | [DeepSeek V3 0324](/models/deepseek__deepseek-chat-v3-0324/) | 1375.0 +143.7 | $0.438/M | 33% | | [GPT-5.4 Nano](/models/openai__gpt-5.4-nano/) | 1372.9 +141.6 | $0.463/M | 29% | | [Qwen3 Next 80B A3B Thinking](/models/qwen__qwen3-next-80b-a3b-thinking/) | 1367.8 +136.5 | $0.412/M | 37% | | [gpt-oss-120b](/models/openai__gpt-oss-120b/) | 1365.9 +134.6 | $0.262/M | 60% | | [MiniMax M2.5](/models/minimax__minimax-m2.5/) | 1358.9 +127.6 | $0.473/M | 27% | | [Gemma 3 27B](/models/google__gemma-3-27b-it/) | 1357.7 +126.4 | $0.172/M | 73% | | [Mercury 2](/models/inception__mercury-2/) | 1357.6 +126.3 | $0.375/M | 42% | | [GLM 4.7 Flash](/models/z-ai__glm-4.7-flash/) | 1352.2 +120.9 | $0.145/M | 78% | | [MiniMax M2](/models/minimax__minimax-m2/) | 1342.1 +110.8 | $0.446/M | 31% | | [Trinity Large Thinking](/models/arcee-ai__trinity-large-thinking/) | 1341.8 +110.5 | $0.388/M | 40% | | [Qwen3 32B](/models/qwen__qwen3-32b/) | 1340.0 +108.7 | $0.130/M | 80% | | [Gemma 3 12B](/models/google__gemma-3-12b-it/) | 1334.2 +102.9 | $0.075/M | 88% | | [DeepSeek V3](/models/deepseek__deepseek-chat/) | 1332.4 +101.1 | $0.463/M | 29% | | [GPT-5 Nano](/models/openai__gpt-5-nano/) | 1319.7 +88.4 | $0.138/M | 79% | | [Qwen3 30B A3B](/models/qwen__qwen3-30b-a3b/) | 1317.0 +85.7 | $0.215/M | 67% | | [Granite 4.2 8B](/models/ibm-granite__granite-4.2-8b/) | 1316.8 +85.5 | $0.107/M | 83% | | [Gemma 3 4B](/models/google__gemma-3-4b-it/) | 1290.7 +59.4 | $0.063/M | 90% | | [gpt-oss-20b](/models/openai__gpt-oss-20b/) | 1287.3 +56.0 | $0.036/M | 94% | | [GPT-4o-mini (2024-07-18)](/models/openai__gpt-4o-mini-2024-07-18/) | 1286.3 +55.0 | $0.262/M | 60% | | [GPT-4.1 Nano](/models/openai__gpt-4.1-nano/) | 1284.7 +53.4 | $0.175/M | 73% | | [Llama 3.3 70B Instruct](/models/meta-llama__llama-3.3-70b-instruct/) | 1274.0 +42.7 | $0.155/M | 76% | | [Qwen2.5 72B Instruct](/models/qwen__qwen-2.5-72b-instruct/) | 1268.9 +37.6 | $0.370/M | 43% | | [Llama 3.1 70B Instruct](/models/meta-llama__llama-3.1-70b-instruct/) | 1260.8 +29.5 | $0.400/M | 38% | | [Mistral Small 3](/models/mistralai__mistral-small-24b-instruct-2501/) | 1233.5 +2.2 | $0.058/M | 91% | 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/)