Alternatives to Command R (08-2024)

Cohere LMArena 1187.3 $0.263/M on a balanced workload prices as of 2026-10-06

31 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, 35 score at least as high as Command R (08-2024) and cost no more under at least one listed workload, with at least one of those dimensions improved. 31 match or beat its recorded context, maximum output, input modes, tool use and extended reasoning. 4 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

Workload	Command R (08-2024) $/M	Recorded capabilities preserved	Recorded capability losses
Balanced	$0.263	25	3
Summarise	$0.173	28	3
Chat	$0.330	27	3
Code gen	$0.420	27	4
Agentic	$0.218	30	3

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	1187.3
Context window	128K
Max output	4K
Input modes	text
Tool use	yes
Extended reasoning	no

Preserving recorded capabilities requires matching or beating these fields. Full record for Command R (08-2024), or check Command R (08-2024) against the whole catalogue.

Recorded capabilities preserved 31

Each option has a higher score or a lower price, with neither dimension worse under the listed workloads. It matches or beats Command R (08-2024) on recorded context, maximum output, input modes, tool use and extended reasoning.

#	Model	Intelligence	$/M	Holds under
1	GLM 5.3 Flash Z.ai	1469.6 +282.3	$0.238	Balanced −10% Summarise −23% Chat −23% Code gen −17% Agentic −40%
2	DeepSeek V4.1 Flash DeepSeek	1462.5 +275.2	$0.182	Balanced −31% Summarise −61% Chat −25% Code gen −14% Agentic −52%
3	MiMo-V2.6-Flash Xiaomi	1456.4 +269.1	$0.175	Balanced −33% Summarise −37% Chat −53% Code gen −49% Agentic −64%
4	Gemma 4 31B Google	1443.4 +256.1	$0.205	Balanced −22% Summarise −11% Chat −26% Code gen −30% Agentic −18%
5	Hy3 Tencent	1440.7 +253.4	$0.231	Balanced −12% Summarise −28% Chat −21% Code gen −14% Agentic −39%
6	Gemma 4 26B A4B Google	1433.9 +246.6	$0.127	Balanced −52% Summarise −60% Chat −55% Code gen −51% Agentic −63%
7	DeepSeek V4 Flash 0423 DeepSeek	1432.1 +244.8	$0.113	Balanced −57% Summarise −57% Chat −68% Code gen −67% Agentic −72%
8	MiMo-V2.5 Xiaomi	1427.5 +240.2	$0.175	Balanced −33% Summarise −37% Chat −53% Code gen −49% Agentic −64%
9	Qwen3 235B A22B Instruct 2507 Qwen	1419.3 +232	$0.205	Balanced −22% Summarise −34% Chat −17% Code gen −13% Agentic −27%
10	Step 3.5 Flash StepFun	1403 +215.7	$0.150	Balanced −43% Summarise −36% Chat −45% Code gen −48% Agentic −40%
11	Qwen3.5-Flash Qwen	1397 +209.7	$0.114	Balanced −57% Summarise −57% Chat −57% Code gen −57% Agentic −57%
12	GPT-6 Luna OpenAI	1391.5 +204.2	$0.200	Balanced −24% Summarise −45% Chat −29% Code gen −21% Agentic −51%
13	Qwen3 30B A3B Instruct 2507 Qwen	1384.1 +196.8	$0.143	Balanced −46% Summarise −42% Chat −47% Code gen −49% Agentic −44%
14	gpt-oss-120b OpenAI	1365.4 +178.1	$0.065	Balanced −75% Summarise −79% Chat −74% Code gen −73% Agentic −77%
15	Gemma 3 27B Google	1357.8 +170.5	$0.100	Balanced −62% Summarise −51% Chat −66% Code gen −70% Agentic −58%
16	GLM 4.7 Flash Z.ai	1350.9 +163.6	$0.145	Balanced −45% Summarise −64% Chat −45% Code gen −38% Agentic −63%
17	Qwen3 32B Qwen	1340.1 +152.8	$0.130	Balanced −50% Summarise −48% Chat −52% Code gen −52% Agentic −49%
18	Gemma 3 12B Google	1334.2 +146.9	$0.075	Balanced −71% Summarise −68% Chat −73% Code gen −74% Agentic −70%
19	GPT-5 Nano OpenAI	1320 +132.7	$0.138	Balanced −48% Summarise −68% Chat −47% Code gen −39% Agentic −65%
20	Granite 4.2 8B IBM	1317.8 +130.5	$0.108	Balanced −59% Summarise −67% Chat −63% Code gen −59% Agentic −72%
21	Qwen3 30B A3B Qwen	1316.6 +129.3	$0.215	Balanced −18% Summarise −19% Chat −18% Code gen −17% Agentic −19%
22	gpt-oss-20b OpenAI	1287.7 +100.4	$0.036	Balanced −86% Summarise −89% Chat −87% Code gen −86% Agentic −89%
23	GPT-4.1 Nano OpenAI	1284.8 +97.5	$0.175	Balanced −33% Summarise −46% Chat −40% Code gen −35% Agentic −54%
24	GPT-4o-mini (2024-07-18) OpenAI	1286.4 +99.1	$0.263	Balanced same price Summarise −12% Chat −7% Code gen −1% Agentic −21%
25	Llama 3.3 70B Instruct Meta	1274.1 +86.8	$0.201	Balanced −23% Summarise −14% Chat −27% Code gen −30% Agentic −20%
26	DeepSeek V3.2 DeepSeek	1424.5 +237.2	$0.269 chat	Chat −18% Code gen −23% Agentic −8%
27	DeepSeek V3.2 Exp DeepSeek	1422.4 +235.1	$0.326 chat	Chat −1% Code gen −16%
28	Qwen3 Next 80B A3B Instruct Qwen	1417.3 +230	$0.132 summarise	Summarise −24% Agentic −8%
29	Qwen3.5-35B-A3B Qwen	1394.4 +207.1	$0.157 summarise	Summarise −9% Agentic −1%
30	GLM 4.5 Air Z.ai	1383.9 +196.6	$0.136 summarise	Summarise −21% Agentic −19%
31	Mercury 2 Inception	1355.2 +167.9	$0.191 agentic	Agentic −12%

Alternatives with recorded capability losses 4

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.

Model	Intelligence	$/M	Holds under	Recorded capability loss
Gemma 3 4B Google	1290.8 +103.5	$0.063	Balanced −76% Summarise −70% Chat −79% Code gen −81% Agentic −74%	no tool use
Mistral Small 3 Mistral	1233.6 +46.3	$0.058	Balanced −78% Summarise −70% Chat −81% Code gen −84% Agentic −75%	128K → 33K context no tool use
Phi 4 Microsoft	1216.7 +29.4	$0.088	Balanced −67% Summarise −57% Chat −70% Code gen −73% Agentic −63%	128K → 16K context no tool use
Qwen2.5 72B Instruct Qwen	1269 +81.7	$0.384 code gen	Code gen −9%	128K → 33K context

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