Alternatives to Gemma 2 27B

Google LMArena 1231.3 $0.650/M on a balanced workload prices as of 2026-10-06

79 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, 79 score at least as high as Gemma 2 27B and cost no more under at least one listed workload, with at least one of those dimensions improved. 79 match or beat its recorded context, maximum output, input modes, tool use and extended reasoning.

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

Workload	Gemma 2 27B $/M	Recorded capabilities preserved
Balanced	$0.650	56
Summarise	$0.650	79
Chat	$0.650	53
Code gen	$0.650	37
Agentic	$0.650	70

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

Intelligence	1231.3
Context window	8K
Max output	2K
Input modes	text
Tool use	no
Extended reasoning	no

Preserving recorded capabilities requires matching or beating these fields. Full record for Gemma 2 27B, or check Gemma 2 27B against the whole catalogue.

Recorded capabilities preserved 79

Each option has a higher score or a lower price, with neither dimension worse under the listed workloads. It matches or beats Gemma 2 27B on recorded context, maximum output, input modes, tool use and extended reasoning.

#	Model	Intelligence	$/M	Holds under
1	MiMo-V2.6-Pro Xiaomi	1491 +259.7	$0.540	Balanced −17% Summarise −49% Chat −26% Agentic −63%
2	GLM 5.3 Flash Z.ai	1469.6 +238.3	$0.238	Balanced −63% Summarise −79% Chat −61% Code gen −46% Agentic −80%
3	DeepSeek V4.1 Flash DeepSeek	1462.5 +231.2	$0.182	Balanced −72% Summarise −90% Chat −62% Code gen −45% Agentic −84%
4	MiMo-V2.5-Pro Xiaomi	1465 +233.7	$0.544	Balanced −16% Summarise −49% Chat −26% Agentic −63%
5	MiMo-V2.6-Flash Xiaomi	1456.4 +225.1	$0.175	Balanced −73% Summarise −83% Chat −76% Code gen −67% Agentic −88%
6	Qwen3.7 Plus Qwen	1454.6 +223.3	$0.560	Balanced −14% Summarise −55% Chat −4% Agentic −52%
7	Gemma 4 31B Google	1443.4 +212.1	$0.205	Balanced −68% Summarise −76% Chat −62% Code gen −54% Agentic −72%
8	Hy3 Tencent	1440.7 +209.4	$0.231	Balanced −64% Summarise −81% Chat −60% Code gen −44% Agentic −80%
9	Qwen3.8 27B Qwen	1440.7 +209.4	$0.562	Balanced −14% Summarise −72% Agentic −43%
10	Gemma 4 26B A4B Google	1433.9 +202.6	$0.127	Balanced −81% Summarise −89% Chat −77% Code gen −69% Agentic −88%
11	DeepSeek V4 Flash 0423 DeepSeek	1432.1 +200.8	$0.113	Balanced −83% Summarise −89% Chat −84% Code gen −79% Agentic −91%
12	MiMo-V2.5 Xiaomi	1427.5 +196.2	$0.175	Balanced −73% Summarise −83% Chat −76% Code gen −67% Agentic −88%
13	MiniMax M3 MiniMax	1432.1 +200.8	$0.485	Balanced −25% Summarise −60% Chat −17% Agentic −59%
14	GPT-5.6 Luna OpenAI	1431 +199.7	$0.450	Balanced −31% Summarise −69% Chat −16% Agentic −63%
15	DeepSeek V3.2 DeepSeek	1424.5 +193.2	$0.290	Balanced −55% Summarise −65% Chat −59% Code gen −51% Agentic −69%
16	DeepSeek V3.2 Exp DeepSeek	1422.4 +191.1	$0.305	Balanced −53% Summarise −57% Chat −50% Code gen −46% Agentic −55%
17	Qwen3 235B A22B Instruct 2507 Qwen	1419.3 +188	$0.205	Balanced −68% Summarise −83% Chat −58% Code gen −44% Agentic −76%
18	Qwen3 VL 235B A22B Instruct Qwen	1420.1 +188.8	$0.370	Balanced −43% Summarise −68% Chat −32% Code gen −8% Agentic −62%
19	Qwen3 Next 80B A3B Instruct Qwen	1417.3 +186	$0.268	Balanced −59% Summarise −80% Chat −43% Code gen −22% Agentic −69%
20	DeepSeek V3.1 DeepSeek	1419.7 +188.4	$0.453	Balanced −30% Summarise −53% Chat −14% Agentic −42%
21	DeepSeek V3.1 Terminus DeepSeek	1417.1 +185.8	$0.453	Balanced −30% Summarise −53% Chat −14% Agentic −42%
22	Gemini 3.1 Flash Lite Preview Google	1415.7 +184.4	$0.563	Balanced −13% Summarise −62% Agentic −53%
23	Inkling Small Thinking Machines	1413.7 +182.4	$0.638	Balanced −2% Summarise −40% Chat −1% Agentic −46%
24	Step 3.5 Flash StepFun	1403 +171.7	$0.150	Balanced −77% Summarise −83% Chat −72% Code gen −66% Agentic −80%
25	Qwen3.5-27B Qwen	1408.9 +177.6	$0.536	Balanced −18% Summarise −60% Agentic −39%
26	MiniMax M2.7 MiniMax	1404.6 +173.3	$0.525	Balanced −19% Summarise −57% Chat −10% Agentic −55%
27	Qwen3.5-Flash Qwen	1397 +165.7	$0.114	Balanced −83% Summarise −89% Chat −78% Code gen −72% Agentic −86%
28	Qwen3.5-35B-A3B Qwen	1394.4 +163.1	$0.355	Balanced −45% Summarise −76% Chat −30% Code gen under 1% less Agentic −67%
29	GPT-6 Luna OpenAI	1391.5 +160.2	$0.200	Balanced −69% Summarise −85% Chat −64% Code gen −49% Agentic −84%
30	Qwen3 30B A3B Instruct 2507 Qwen	1384.1 +152.8	$0.143	Balanced −78% Summarise −85% Chat −73% Code gen −67% Agentic −81%
31	GLM 4.5 Air Z.ai	1383.9 +152.6	$0.310	Balanced −52% Summarise −79% Chat −41% Code gen −15% Agentic −73%
32	Solar Pro 4 Upstage	1386.2 +154.9	$0.525	Balanced −19% Summarise −57% Chat −10% Agentic −55%
33	GLM 4.6V Z.ai	1376.8 +145.5	$0.450	Balanced −31% Summarise −60% Chat −28% Code gen −2% Agentic −63%
34	DeepSeek V3 0324 DeepSeek	1375 +143.7	$0.438	Balanced −33% Summarise −56% Chat −15% Agentic −44%
35	GPT-5.4 Nano OpenAI	1372.1 +140.8	$0.463	Balanced −29% Summarise −69% Chat −13% Agentic −61%
36	gpt-oss-120b OpenAI	1365.4 +134.1	$0.065	Balanced −90% Summarise −94% Chat −87% Code gen −82% Agentic −92%
37	Qwen3 Next 80B A3B Thinking Qwen	1368.3 +137	$0.413	Balanced −37% Summarise −69% Chat −12% Agentic −53%
38	Gemma 3 27B Google	1357.8 +126.5	$0.100	Balanced −85% Summarise −87% Chat −83% Code gen −80% Agentic −86%
39	MiniMax M2.5 MiniMax	1359.3 +128	$0.521	Balanced −20% Summarise −58% Chat −10% Agentic −55%
40	Mercury 2 Inception	1355.2 +123.9	$0.375	Balanced −42% Summarise −68% Chat −41% Code gen −18% Agentic −71%
41	GLM 4.7 Flash Z.ai	1350.9 +119.6	$0.145	Balanced −78% Summarise −90% Chat −72% Code gen −60% Agentic −88%
42	Qwen3 32B Qwen	1340.1 +108.8	$0.130	Balanced −80% Summarise −86% Chat −75% Code gen −69% Agentic −83%
43	Trinity Large Thinking Arcee	1340 +108.7	$0.388	Balanced −40% Summarise −66% Chat −36% Code gen −13% Agentic −66%
44	Gemma 3 12B Google	1334.2 +102.9	$0.075	Balanced −88% Summarise −92% Chat −86% Code gen −83% Agentic −90%
45	MiniMax M2 MiniMax	1339.9 +108.6	$0.525	Balanced −19% Summarise −59% Chat −11% Agentic −58%
46	DeepSeek V3 DeepSeek	1332.5 +101.2	$0.500	Balanced −23% Summarise −49% Chat −3% Agentic −36%
47	GPT-5 Nano OpenAI	1320 +88.7	$0.138	Balanced −79% Summarise −92% Chat −73% Code gen −61% Agentic −88%
48	Granite 4.2 8B IBM	1317.8 +86.5	$0.108	Balanced −83% Summarise −91% Chat −81% Code gen −74% Agentic −91%
49	Qwen3 30B A3B Qwen	1316.6 +85.3	$0.215	Balanced −67% Summarise −79% Chat −58% Code gen −46% Agentic −73%
50	Gemma 3 4B Google	1290.8 +59.5	$0.063	Balanced −90% Summarise −92% Chat −89% Code gen −88% Agentic −91%
51	gpt-oss-20b OpenAI	1287.7 +56.4	$0.036	Balanced −94% Summarise −97% Chat −93% Code gen −91% Agentic −96%
52	GPT-4o-mini (2024-07-18) OpenAI	1286.4 +55.1	$0.263	Balanced −60% Summarise −77% Chat −53% Code gen −36% Agentic −73%
53	GPT-4.1 Nano OpenAI	1284.8 +53.5	$0.175	Balanced −73% Summarise −86% Chat −70% Code gen −58% Agentic −85%
54	Llama 3.3 70B Instruct Meta	1274.1 +42.8	$0.201	Balanced −69% Summarise −77% Chat −63% Code gen −55% Agentic −73%
55	Qwen2.5 72B Instruct Qwen	1269 +37.7	$0.370	Balanced −43% Summarise −44% Chat −42% Code gen −41% Agentic −44%
56	Mistral Small 3 Mistral	1233.6 tie	$0.058	Balanced −91% Summarise −92% Chat −90% Code gen −90% Agentic −92%
57	GLM 5.3 Z.ai	1471.4 +240.1	$0.346 summarise	Summarise −47%
58	GLM 5.2 Z.ai	1470.4 +239.1	$0.422 summarise	Summarise −35%
59	Kimi K2.6 Moonshot AI	1455.5 +224.2	$0.460 summarise	Summarise −29% Agentic −16%
60	DeepSeek V4 Pro 0423 DeepSeek	1445.2 +213.9	$0.502 summarise	Summarise −23%
61	GLM 5 Z.ai	1446.3 +215	$0.617 summarise	Summarise −5% Agentic −8%
62	Kimi K2.5 Moonshot AI	1445.2 +213.9	$0.578 summarise	Summarise −11%
63	GLM 4.6 Z.ai	1439.9 +208.6	$0.396 summarise	Summarise −39% Agentic −35%
64	Qwen3.5 397B A17B Qwen	1438 +206.7	$0.488 summarise	Summarise −25%
65	Qwen3.6 Plus Qwen	1436.7 +205.4	$0.406 summarise	Summarise −38% Agentic −13%
66	GLM 4.7 Z.ai	1435.5 +204.2	$0.376 summarise	Summarise −42% Agentic −37%
67	Gemini 3.5 Flash Lite Google	1434.7 +203.4	$0.333 summarise	Summarise −49% Agentic −28%
68	GLM 4.5 Z.ai	1430.3 +199	$0.540 summarise	Summarise −17% Agentic −16%
69	R1 0528 DeepSeek	1427.9 +196.6	$0.584 summarise	Summarise −10%
70	Gemini 2.5 Flash Google	1417 +185.7	$0.333 summarise	Summarise −49% Agentic −28%
71	Qwen3.5-122B-A10B Qwen	1417.1 +185.8	$0.351 summarise	Summarise −46% Agentic −18%
72	Qwen3 235B A22B Thinking 2507 Qwen	1415.2 +183.9	$0.334 summarise	Summarise −49% Agentic −17%
73	Qwen3 VL 235B A22B Thinking Qwen	1400.7 +169.4	$0.580 summarise	Summarise −11%
74	GPT-5 Mini OpenAI	1373.2 +141.9	$0.273 summarise	Summarise −58% Agentic −42%
75	Qwen3 235B A22B Qwen	1366.6 +135.3	$0.523 summarise	Summarise −20%
76	Nova 2 Lite Amazon	1361.8 +130.5	$0.410 summarise	Summarise −37% Agentic −3%
77	MiniMax M1 MiniMax	1342.8 +111.5	$0.490 summarise	Summarise −25%
78	GPT-4.1 Mini OpenAI	1340.4 +109.1	$0.375 summarise	Summarise −42% Agentic −38%
79	GLM 4.5V Z.ai	1332.8 +101.5	$0.520 summarise	Summarise −20% Agentic −25%

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.

Choose models

Compare costs

Build with AI

Understand the numbers

Check our work

Reuse the data