CompareLLM.ai
Live
Leaderboard
Models
Compare
Best of & Stacks
Research & News
…
CompareLLM.ai
Precision Benchmarks

Programmatic, dated AI model benchmarks, head-to-head comparisons, and Stack Engine presets.

Daily ingest · 06:00 UTC

Analytics & Benchmarks

  • AI Model Leaderboard
  • Head-to-Head Compare Hub
  • Models Directory
  • Stack Engine Presets
  • Frontier Models
  • Open Weights Catalog

Guides & Intent Lists

  • Best LLM Lists (2026)
  • Best Coding LLM
  • Best Cheap LLM
  • Fastest Low-Latency LLM
  • Claude vs GPT Benchmark
  • What is Elo?
  • Methodology Guides
  • News & Dispatches

Transparency & API

  • Evaluation Methodology
  • Benchmark Changelog
  • Public JSON API
  • llms.txt Specification
  • Privacy Policy
  • Sign In / Account

© 2026 CompareLLM. Public benchmark data aggregated from Arena Elo, LiveBench, SWE-bench & OpenRouter.

Every score has a dated snapshot.

Theme:
Currency:
  1. Home
  2. Providers
  3. OpenAI
AI Provider Portfolio
16 active models in catalog

OpenAI Models

Comprehensive benchmark scores, coding performance, latency metrics, and API pricing for all models developed by OpenAI.

Flagship ModelGPT-5.6 Sol
Portfolio Avg Elo1459 Elo
Browse Other Providers
AnthropicGooglexAI

Available Models & Verified Benchmarks

#1GPT-5.6 Sol
Proprietary

OpenAI 5.6 flagship tier. Official API $5/$30 per 1M tokens (OpenAI pricing, Jul 30 2026 update left Sol unchanged).

Elo1,608
SWE-bench77.6%
Out $/1M$30
Model Fact Sheetvs all hub
#2OpenAI o3-mini
Proprietary

OpenAI cost-efficient reasoning model with adjustable thinking effort and top coding benchmark scores.

Elo1,560
SWE-bench78.5%
Out $/1M$4.4
Model Fact Sheetvs all hub
#3GPT-5
Proprietary

OpenAI flagship reasoning model for 2025–26. Strong general preference Elo and multimodal coverage.

Elo1,558
SWE-bench68.4%
Out $/1M$20
Model Fact Sheetvs all hub
#4GPT-5.6 Terra
Proprietary

OpenAI 5.6 mid tier. Official API $2/$12 per 1M after the Jul 30 2026 price cut.

Elo1,548
SWE-bench70.4%
Out $/1M$12
Model Fact Sheetvs all hub
#5GPT-4.5 Orion
Proprietary

OpenAI largest dense non-reasoning model with expansive world knowledge and reduced hallucinations.

Elo1,540
SWE-bench71%
Out $/1M$150
Model Fact Sheetvs all hub
#6OpenAI o1
Proprietary

OpenAI pioneer reasoning foundation model designed for complex science, math, and multi-step reasoning.

Elo1,512
SWE-bench48.9%
Out $/1M$60
Model Fact Sheetvs all hub
#7GPT-5.6 Luna
Proprietary

OpenAI 5.6 fast/cheap tier. Official API $0.20/$1.20 per 1M after the Jul 30 80% Luna cut.

Elo1,466
SWE-bench61.8%
Out $/1M$1.2
Model Fact Sheetvs all hub
#8OpenAI o1-mini
Proprietary

OpenAI high-speed, cost-effective reasoning model optimized for STEM, math, and code generation.

Elo1,445
SWE-bench56.4%
Out $/1M$4.4
Model Fact Sheetvs all hub
#9GPT-5 mini
Proprietary

Cost-efficient GPT-5 distill for high-volume agents.

Elo1,410
SWE-bench52.4%
Out $/1M$2
Model Fact Sheetvs all hub
#10GPT-4o
Proprietary

Previous OpenAI flagship. Still a common compare baseline on legacy pages.

Elo1,335
SWE-bench54.8%
Out $/1M$10
Model Fact Sheetvs all hub
#11GPT-4o mini
Proprietary

Legacy small OpenAI model. Useful as a cheap baseline.

Elo1,272
SWE-bench41.2%
Out $/1M$0.6
Model Fact Sheetvs all hub
#12GPT-4 Turbo
Proprietary

GPT-4 Turbo 128k. Historical flagship for gpt-4 turbo vs gpt-4o / gpt-5.

Elo1,255
SWE-bench33.2%
Out $/1M$30
Model Fact Sheetvs all hub
#13GPT Image 2 (High)
Proprietary

OpenAI flagship diffusion-transformer image synthesis model with supreme prompt adherence, realistic textures, and complex text composition.

Elo—
SWE-bench—
Out $/1M—
Model Fact Sheetvs all hub
#14GPT Image 2 (Low / Fast)
Proprietary

Fast distilled tier of GPT Image 2 designed for high-throughput interactive creative workflows at 70% lower price.

Elo—
SWE-bench—
Out $/1M—
Model Fact Sheetvs all hub
#15GPT Image 1.5
Proprietary

Previous OpenAI image generation flagship. High fidelity with proven enterprise reliability.

Elo—
SWE-bench—
Out $/1M—
Model Fact Sheetvs all hub
#16DALL-E 3
Proprietary

Legacy OpenAI image model benchmark baseline. Retained for historical comparisons.

Elo—
SWE-bench—
Out $/1M—
Model Fact Sheetvs all hub