Alternatives to o3

OpenAI LMArena 1409.9 $3.50/M on a balanced workload prices as of 2026-10-06

10 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, 59 score at least as high as o3 and cost no more under at least one listed workload, with at least one of those dimensions improved. 10 match or beat its recorded context, maximum output, input modes, tool use and extended reasoning. 49 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	o3 $/M	Recorded capabilities preserved	Recorded capability losses
Balanced	$3.50	9	48
Summarise	$1.87	10	49
Chat	$3.95	8	46
Code gen	$5.48	8	46
Agentic	$2.01	8	48

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	1409.9
Context window	200K
Max output	100K
Input modes	image, text, file
Tool use	yes
Extended reasoning	yes

Preserving recorded capabilities requires matching or beating these fields. Full record for o3, or check o3 against the whole catalogue.

Recorded capabilities preserved 10

Each option has a higher score or a lower price, with neither dimension worse under the listed workloads. It matches or beats o3 on recorded context, maximum output, input modes, tool use and extended reasoning.

#	Model	Intelligence	$/M	Holds under
1	Muse Spark 1.3 Meta	1489.9 +80	$2.00	Balanced −43% Summarise −42% Chat −46% Code gen −46% Agentic −48%
2	Muse Spark 1.2 Meta	1483.2 +73.3	$2.00	Balanced −43% Summarise −42% Chat −46% Code gen −46% Agentic −48%
3	Muse Spark 1.1 Meta	1479.2 +69.3	$2.00	Balanced −43% Summarise −42% Chat −46% Code gen −46% Agentic −48%
4	Grok 4.5 xAI	1448.1 +38.2	$3.00	Balanced −14% Summarise −8% Chat −22% Code gen −22% Agentic −21%
5	GPT-5.6 Luna OpenAI	1431 +21.1	$0.450	Balanced −87% Summarise −89% Chat −86% Code gen −86% Agentic −88%
6	Grok 4.6 xAI	1427.4 +17.5	$3.00	Balanced −14% Summarise −5% Chat −20% Code gen −22% Agentic −15%
7	Mistral Medium 3.5 Mistral	1421.2 +11.3	$3.00	Balanced −14% Summarise −4% Chat −1% Code gen −7%
8	GPT-5.1 OpenAI	1422.2 +12.3	$3.44	Balanced −2% Summarise −27% Agentic −6%
9	GPT-5.4 Mini OpenAI	1411.4 tie	$1.69	Balanced −52% Summarise −60% Chat −48% Code gen −46% Agentic −55%
10	GPT-6.1 Sol OpenAI	1445.6 +35.7	$1.86 summarise	Summarise −1%

Alternatives with recorded capability losses 49

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
MiMo-V2.6-Pro Xiaomi	1491 +81.1	$0.540	Balanced −85% Summarise −82% Chat −88% Code gen −88% Agentic −88%	no file input
Gemini 3.8 Flash Google	1497 +87.1	$3.00	Balanced −14% Summarise −24% Chat −12% Code gen −9% Agentic −20%	100K → 66K max output
Gemini 3.7 Flash Google	1487 +77.1	$3.00	Balanced −14% Summarise −24% Chat −12% Code gen −9% Agentic −20%	100K → 66K max output
Gemini 3.6 Flash Google	1479.5 +69.6	$1.50	Balanced −57% Summarise −62% Chat −56% Code gen −54% Agentic −60%	100K → 66K max output
GLM 5.3 Flash Z.ai	1469.6 +59.7	$0.238	Balanced −93% Summarise −93% Chat −94% Code gen −94% Agentic −93%	no file input
GLM 5.3 Z.ai	1471.4 +61.5	$1.00	Balanced −71% Summarise −82% Chat −63% Code gen −61% Agentic −68%	no image, file input
Gemini 3.5 Flash Google	1477.7 +67.8	$3.38	Balanced −4% Summarise −20% Agentic −9%	100K → 66K max output
GLM 5.2 Z.ai	1470.4 +60.5	$1.12	Balanced −68% Summarise −77% Chat −61% Code gen −59% Agentic −65%	no image, file input
MiMo-V2.5-Pro Xiaomi	1465 +55.1	$0.544	Balanced −84% Summarise −82% Chat −88% Code gen −88% Agentic −88%	no image, file input
DeepSeek V4.1 Flash DeepSeek	1462.5 +52.6	$0.182	Balanced −95% Summarise −96% Chat −94% Code gen −93% Agentic −95%	no file input
GLM 5.1 Z.ai	1461.5 +51.6	$1.83	Balanced −48% Summarise −39% Chat −49% Code gen −51% Agentic −39%	no image, file input
MiMo-V2.6-Flash Xiaomi	1456.4 +46.5	$0.175	Balanced −95% Summarise −94% Chat −96% Code gen −96% Agentic −96%	no file input
Qwen3.7 Plus Qwen	1454.6 +44.7	$0.560	Balanced −84% Summarise −84% Chat −84% Code gen −84% Agentic −84%	no file input
Kimi K2.6 Moonshot AI	1455.5 +45.6	$0.961	Balanced −73% Summarise −75% Chat −71% Code gen −70% Agentic −73%	no file input
Gemini 2.5 Pro Google	1457.8 +47.9	$3.44	Balanced −2% Summarise −27% Agentic −6%	100K → 66K max output
GLM 5 Z.ai	1446.3 +36.4	$1.09	Balanced −69% Summarise −67% Chat −71% Code gen −71% Agentic −70%	no image, file input
Gemma 4 31B Google	1443.4 +33.5	$0.205	Balanced −94% Summarise −92% Chat −94% Code gen −95% Agentic −91%	100K → 16K max output no file input
Kimi K2.5 Moonshot AI	1445.2 +35.3	$1.20	Balanced −66% Summarise −69% Chat −64% Code gen −64% Agentic −67%	no file input
DeepSeek V4 Pro 0423 DeepSeek	1445.2 +35.3	$1.21	Balanced −66% Summarise −73% Chat −61% Code gen −59% Agentic −65%	no image, file input
Qwen3.6 Max Preview Qwen	1446.8 +36.9	$2.31	Balanced −34% Summarise −31% Chat −22% Code gen −25% Agentic −10%	100K → 66K max output no image, file input
Hy3 Tencent	1440.7 +30.8	$0.231	Balanced −93% Summarise −93% Chat −93% Code gen −93% Agentic −93%	no image, file input
Qwen3.8 27B Qwen	1440.7 +30.8	$0.562	Balanced −84% Summarise −90% Chat −79% Code gen −78% Agentic −82%	no file input
GLM 4.6 Z.ai	1439.9 +30	$0.760	Balanced −78% Summarise −79% Chat −78% Code gen −78% Agentic −79%	100K → 16K max output no image, file input
Inkling Thinking Machines	1441.8 +31.9	$1.73	Balanced −51% Summarise −53% Chat −51% Code gen −50% Agentic −53%	no file input
Qwen3.5 397B A17B Qwen	1438 +28.1	$0.878	Balanced −75% Summarise −74% Chat −70% Code gen −72% Agentic −66%	100K → 82K max output no file input
Qwen3.6 Plus Qwen	1436.7 +26.8	$0.731	Balanced −79% Summarise −78% Chat −75% Code gen −76% Agentic −72%	100K → 66K max output no file input
Gemma 4 26B A4B Google	1433.9 +24	$0.127	Balanced −96% Summarise −96% Chat −96% Code gen −96% Agentic −96%	no file input
GLM 4.7 Z.ai	1435.5 +25.6	$0.738	Balanced −79% Summarise −80% Chat −79% Code gen −78% Agentic −79%	no image, file input
Gemini 3.5 Flash Lite Google	1434.7 +24.8	$0.850	Balanced −76% Summarise −82% Chat −72% Code gen −71% Agentic −77%	100K → 66K max output
DeepSeek V4 Flash 0423 DeepSeek	1432.1 +22.2	$0.113	Balanced −97% Summarise −96% Chat −97% Code gen −97% Agentic −97%	no image, file input
GLM 5V Turbo Z.ai	1437.2 +27.3	$1.90	Balanced −46% Summarise −43% Chat −49% Code gen −49% Agentic −48%	no file input
MiniMax M3 MiniMax	1432.1 +22.2	$0.485	Balanced −86% Summarise −86% Chat −86% Code gen −86% Agentic −87%	no file input
GLM 4.5 Z.ai	1430.3 +20.4	$1.00	Balanced −71% Summarise −71% Chat −72% Code gen −72% Agentic −73%	200K → 131K context 100K → 98K max output no image, file input
MiMo-V2.5 Xiaomi	1427.5 +17.6	$0.175	Balanced −95% Summarise −94% Chat −96% Code gen −96% Agentic −96%	no file input
R1 0528 DeepSeek	1427.9 +18	$0.920	Balanced −74% Summarise −69% Chat −70% Code gen −72% Agentic −63%	200K → 164K context 100K → 33K max output no image, file input
DeepSeek V3.2 DeepSeek	1424.5 +14.6	$0.290	Balanced −92% Summarise −88% Chat −93% Code gen −94% Agentic −90%	200K → 164K context 100K → 66K max output no image, file input
DeepSeek V3.2 Exp DeepSeek	1422.4 +12.5	$0.305	Balanced −91% Summarise −85% Chat −92% Code gen −94% Agentic −86%	200K → 164K context no image, file input
Qwen3 VL 235B A22B Instruct Qwen	1420.1 tie	$0.370	Balanced −89% Summarise −89% Chat −89% Code gen −89% Agentic −88%	100K → 33K max output no file input no extended reasoning
Qwen3 235B A22B Instruct 2507 Qwen	1419.3 tie	$0.205	Balanced −94% Summarise −94% Chat −93% Code gen −93% Agentic −92%	100K → 16K max output no image, file input no extended reasoning
DeepSeek V3.1 DeepSeek	1419.7 tie	$0.453	Balanced −87% Summarise −84% Chat −86% Code gen −87% Agentic −81%	200K → 164K context 100K → 33K max output no image, file input
Qwen3 Next 80B A3B Instruct Qwen	1417.3 tie	$0.268	Balanced −92% Summarise −93% Chat −91% Code gen −91% Agentic −90%	no image, file input no extended reasoning
DeepSeek V3.1 Terminus DeepSeek	1417.1 tie	$0.453	Balanced −87% Summarise −84% Chat −86% Code gen −87% Agentic −81%	200K → 164K context no image, file input
Qwen3.5-122B-A10B Qwen	1417.1 tie	$0.715	Balanced −80% Summarise −81% Chat −75% Code gen −75% Agentic −73%	100K → 66K max output no file input
Gemini 2.5 Flash Google	1417 tie	$0.850	Balanced −76% Summarise −82% Chat −72% Code gen −71% Agentic −77%	100K → 66K max output
Gemini 3.1 Flash Lite Preview Google	1415.7 tie	$0.563	Balanced −84% Summarise −87% Chat −83% Code gen −82% Agentic −85%	100K → 66K max output
Qwen3 235B A22B Thinking 2507 Qwen	1415.2 tie	$0.748	Balanced −79% Summarise −82% Chat −73% Code gen −73% Agentic −73%	200K → 131K context no image, file input
Inkling Small Thinking Machines	1413.7 tie	$0.638	Balanced −82% Summarise −79% Chat −84% Code gen −84% Agentic −82%	no file input
Qwen3 Max Qwen	1412.4 tie	$1.56	Balanced −55% Summarise −60% Chat −53% Code gen −53% Agentic −56%	100K → 66K max output no image, file input
Kimi K3 Moonshot AI	1475.9 +66	$1.23 summarise	Summarise −34%	no file input

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