Undominated.ai

Alternatives to GPT-4o-mini (2024-07-18)

OpenAI LMArena 1286.4 $0.263/M on a balanced workload prices as of 2026-10-06

2 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, 27 score at least as high as GPT-4o-mini (2024-07-18) and cost no more under at least one listed workload, with at least one of those dimensions improved. 2 match or beat its recorded context, maximum output, input modes, tool use and extended reasoning. 25 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

WorkloadGPT-4o-mini (2024-07-18) $/MRecorded capabilities preservedRecorded capability losses
Balanced$0.263221
Summarise$0.151222
Chat$0.308222
Code gen$0.414223
Agentic$0.173219

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

Intelligence1286.4
Context window128K
Max output16K
Input modestext, image, file
Tool useyes
Extended reasoningno

Preserving recorded capabilities requires matching or beating these fields. Full record for GPT-4o-mini (2024-07-18), or check GPT-4o-mini (2024-07-18) against the whole catalogue.

Recorded capabilities preserved 2

Each option has a higher score or a lower price, with neither dimension worse under the listed workloads. It matches or beats GPT-4o-mini (2024-07-18) on recorded context, maximum output, input modes, tool use and extended reasoning.

#ModelIntelligence$/MHolds under
1GPT-6 Luna OpenAI1391.5 +105.1$0.200
  • Balanced −24%
  • Summarise −38%
  • Chat −24%
  • Code gen −20%
  • Agentic −38%
2GPT-5 Nano OpenAI1320 +33.6$0.138
  • Balanced −48%
  • Summarise −64%
  • Chat −43%
  • Code gen −38%
  • Agentic −56%

Alternatives with recorded capability losses 25

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.

ModelIntelligence$/MHolds underRecorded capability loss
GLM 5.3 Flash Z.ai1469.6 +183.2$0.238
  • Balanced −10%
  • Summarise −12%
  • Chat −17%
  • Code gen −15%
  • Agentic −24%
  • no file input
DeepSeek V4.1 Flash DeepSeek1462.5 +176.1$0.182
  • Balanced −31%
  • Summarise −56%
  • Chat −20%
  • Code gen −13%
  • Agentic −39%
  • no file input
MiMo-V2.6-Flash Xiaomi1456.4 +170$0.175
  • Balanced −33%
  • Summarise −29%
  • Chat −50%
  • Code gen −49%
  • Agentic −54%
  • no file input
Gemma 4 31B Google1443.4 +157$0.205
  • Balanced −22%
  • Chat −21%
  • Code gen −29%
  • no file input
Hy3 Tencent1440.7 +154.3$0.231
  • Balanced −12%
  • Summarise −18%
  • Chat −15%
  • Code gen −13%
  • Agentic −23%
  • no image, file input
Gemma 4 26B A4B Google1433.9 +147.5$0.127
  • Balanced −52%
  • Summarise −54%
  • Chat −51%
  • Code gen −51%
  • Agentic −54%
  • no file input
DeepSeek V4 Flash 0423 DeepSeek1432.1 +145.7$0.113
  • Balanced −57%
  • Summarise −51%
  • Chat −66%
  • Code gen −67%
  • Agentic −65%
  • no image, file input
MiMo-V2.5 Xiaomi1427.5 +141.1$0.175
  • Balanced −33%
  • Summarise −29%
  • Chat −50%
  • Code gen −49%
  • Agentic −54%
  • no file input
Qwen3 235B A22B Instruct 2507 Qwen1419.3 +132.9$0.205
  • Balanced −22%
  • Summarise −25%
  • Chat −11%
  • Code gen −12%
  • Agentic −8%
  • no image, file input
Step 3.5 Flash StepFun1403 +116.6$0.150
  • Balanced −43%
  • Summarise −27%
  • Chat −41%
  • Code gen −47%
  • Agentic −25%
  • no image, file input
Qwen3.5-Flash Qwen1397 +110.6$0.114
  • Balanced −57%
  • Summarise −51%
  • Chat −53%
  • Code gen −56%
  • Agentic −45%
  • no file input
Qwen3 30B A3B Instruct 2507 Qwen1384.1 +97.7$0.143
  • Balanced −46%
  • Summarise −33%
  • Chat −43%
  • Code gen −48%
  • Agentic −30%
  • no image, file input
gpt-oss-120b OpenAI1365.4 +79$0.065
  • Balanced −75%
  • Summarise −76%
  • Chat −72%
  • Code gen −72%
  • Agentic −70%
  • no image, file input
Gemma 3 27B Google1357.8 +71.4$0.100
  • Balanced −62%
  • Summarise −44%
  • Chat −64%
  • Code gen −69%
  • Agentic −47%
  • no file input
GLM 4.7 Flash Z.ai1350.9 +64.5$0.145
  • Balanced −45%
  • Summarise −58%
  • Chat −41%
  • Code gen −37%
  • Agentic −53%
  • no image, file input
Qwen3 32B Qwen1340.1 +53.7$0.130
  • Balanced −50%
  • Summarise −40%
  • Chat −48%
  • Code gen −52%
  • Agentic −36%
  • no image, file input
Gemma 3 12B Google1334.2 +47.8$0.075
  • Balanced −71%
  • Summarise −64%
  • Chat −71%
  • Code gen −73%
  • Agentic −62%
  • no file input
Granite 4.2 8B IBM1317.8 +31.4$0.108
  • Balanced −59%
  • Summarise −62%
  • Chat −60%
  • Code gen −59%
  • Agentic −64%
  • no image, file input
Qwen3 30B A3B Qwen1316.6 +30.2$0.215
  • Balanced −18%
  • Summarise −8%
  • Chat −12%
  • Code gen −16%
  • no image, file input
Gemma 3 4B Google1290.8 tie$0.063
  • Balanced −76%
  • Summarise −65%
  • Chat −77%
  • Code gen −81%
  • Agentic −67%
  • no file input
  • no tool use
gpt-oss-20b OpenAI1287.7 tie$0.036
  • Balanced −86%
  • Summarise −87%
  • Chat −86%
  • Code gen −85%
  • Agentic −86%
  • no image, file input
DeepSeek V3.2 DeepSeek1424.5 +138.1$0.269 chat
  • Chat −13%
  • Code gen −22%
  • no image, file input
DeepSeek V3.2 Exp DeepSeek1422.4 +136$0.354 code gen
  • Code gen −14%
  • no image, file input
Qwen3 Next 80B A3B Instruct Qwen1417.3 +130.9$0.132 summarise
  • Summarise −13%
  • no image, file input
GLM 4.5 Air Z.ai1383.9 +97.5$0.136 summarise
  • Summarise −10%
  • no image, 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.
Evidence & Ask
Markdown for LLMs