GPT-5by OpenAI
2025-08-07
openai/gpt-5
Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows
- Context
- 400K
- Input
- $1.25/M
- Output
- $10/M
Model catalog
Compare AI models
Filter 31 source-linked models by creator, price, context, modality, and published benchmark coverage.
Ranked by raw score for Aider Polyglot - . Versions are kept separate, and incompatible results are never combined.
o3-proby OpenAI
2025-06-10
openai/o3-pro
High-effort o3 tier for difficult technical reasoning and careful answers
- Context
- 200K
- Input
- $20/M
- Output
- $80/M
Gemini 2.5 Proby Google
2025-06-17
google/gemini-2.5-pro
Google's proven reasoning model for coding, math, and multimodal analysis
- Context
- 1.04858M
- Input
- $1.25/M
- Output
- $10/M
o3by OpenAI
2025-04-16
openai/o3
Deliberate o-series reasoner for hard math, coding, and multi-step analysis
- Context
- 200K
- Input
- $2/M
- Output
- $8/M
DeepSeek Reasonerby DeepSeek
2025-12-01
deepseek/deepseek-reasoner
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
- Context
- 1M
- Input
- $0.14/M
- Output
- $0.28/M
Claude Opus 4 (latest)by Anthropic
2025-05-22
anthropic/claude-opus-4-0
Flagship Claude model for deep reasoning, coding, and long-horizon agents
- Context
- 200K
- Input
- $15/M
- Output
- $75/M
Claude Opus 4by Anthropic
2025-05-22
anthropic/claude-opus-4-20250514
Flagship Claude model for deep reasoning, coding, and long-horizon agents
- Context
- 200K
- Input
- $15/M
- Output
- $75/M
o4-miniby OpenAI
2025-04-16
openai/o4-mini
Fast o-series model for compact reasoning, coding, and tool use
- Context
- 200K
- Input
- $1.1/M
- Output
- $4.4/M
DeepSeek Chatby DeepSeek
2025-12-01
deepseek/deepseek-chat
DeepSeek chat model for instruction following, coding, and analysis
- Context
- 1M
- Input
- $0.14/M
- Output
- $0.28/M
Claude Sonnet 3.7by Anthropic
2025-02-19
anthropic/claude-3-7-sonnet-20250219
Balanced Claude model for coding, analysis, agent workflows, and cost control
- Context
- 200K
- Input
- $3/M
- Output
- $15/M
o1by OpenAI
2024-12-05
openai/o1
O-series reasoning model for hard analysis, math, coding, and planning
- Context
- 200K
- Input
- $15/M
- Output
- $60/M
Claude Sonnet 4 (latest)by Anthropic
2025-05-22
anthropic/claude-sonnet-4-0
Balanced Claude model for coding, analysis, agent workflows, and cost control
- Context
- 200K
- Input
- $3/M
- Output
- $15/M
Claude Sonnet 4by Anthropic
2025-05-22
anthropic/claude-sonnet-4-20250514
Balanced Claude model for coding, analysis, agent workflows, and cost control
- Context
- 200K
- Input
- $3/M
- Output
- $15/M
o3-miniby OpenAI
2024-12-20
openai/o3-mini
Smaller o-series reasoner for economical coding, math, and planning tasks
- Context
- 200K
- Input
- $1.1/M
- Output
- $4.4/M
Qwen3 235B-A22Bby Alibaba Qwen
2025-04
alibaba/qwen3-235b-a22b
Large open Qwen MoE for multilingual reasoning, coding, and tool use
- Context
- 131.072K
- Input
- $0.7/M
- Output
- $2.8/M
DeepSeek-R1by DeepSeek
2025-01-20
deepseek/deepseek-r1
Classic open reasoning model for transparent math, coding, and deliberate problem solving
- Context
- 128K
- Input
- $0.7/M
- Output
- $2.5/M
Gemini 2.5 Flashby Google
2025-06-17
google/gemini-2.5-flash
Fast Gemini workhorse for multimodal apps where latency and price matter
- Context
- 1.04858M
- Input
- $0.3/M
- Output
- $2.5/M
GPT-4.1by OpenAI
2025-04-14
openai/gpt-4.1
Long-lived GPT workhorse for coding, instruction following, and production apps
- Context
- 1.04758M
- Input
- $2/M
- Output
- $8/M
Claude Sonnet 3.5 v2by Anthropic
2024-10-22
anthropic/claude-3-5-sonnet-20241022
Balanced Claude model for coding, analysis, agent workflows, and cost control
- Context
- 200K
- Input
- $3/M
- Output
- $15/M
Qwen3 32Bby Alibaba Qwen
2025-04
alibaba/qwen3-32b
Dense open Qwen model for self-hosted chat, reasoning, and coding
- Context
- 131.072K
- Input
- $0.7/M
- Output
- $2.8/M
GPT-4.1 miniby OpenAI
2025-04-14
openai/gpt-4.1-mini
Affordable GPT-4.1 lane for fast coding help and structured extraction
- Context
- 1.04758M
- Input
- $0.4/M
- Output
- $1.6/M
Claude Haiku 3.5by Anthropic
2024-10-22
anthropic/claude-3-5-haiku-20241022
Fast Claude model for responsive assistance, classification, and lightweight agents
- Context
- 200K
- Input
- $0.8/M
- Output
- $4/M
GPT-4oby OpenAI
2024-05-13
openai/gpt-4o
Omni-era GPT for multimodal chat, practical coding, and general assistants
- Context
- 128K
- Input
- $2.5/M
- Output
- $10/M
GPT-4o (2024-08-06)by OpenAI
2024-08-06
openai/gpt-4o-2024-08-06
GPT model for general reasoning, writing, coding, and tool-assisted tasks
- Context
- 128K
- Input
- $2.5/M
- Output
- $10/M
Qwen Maxby Alibaba Qwen
2024-04-03
alibaba/qwen-max
Flagship Qwen model for complex reasoning, coding, and agentic workflows
- Context
- 32.768K
- Input
- $1.6/M
- Output
- $6.4/M
GPT-4o (2024-11-20)by OpenAI
2024-11-20
openai/gpt-4o-2024-11-20
GPT model for general reasoning, writing, coding, and tool-assisted tasks
- Context
- 128K
- Input
- $2.5/M
- Output
- $10/M
2025-04-05
meta/llama-4-maverick-17b-instruct
Open multimodal Llama for strong reasoning with efficient everyday serving
- Context
- 1M
- Input
- $0.124/M
- Output
- $0.603/M
Command Aby Cohere
2025-03-13
cohere/command-a-03-2025
Cohere command model for multilingual enterprise agents, tools, and chat
- Context
- 256K
- Input
- $2.5/M
- Output
- $10/M
Codestral (latest)by Mistral AI
2024-05-29
mistral/codestral-latest
Mistral code model for completions, refactors, and developer IDE workflows
- Context
- 256K
- Input
- $0.3/M
- Output
- $0.9/M
GPT-4.1 nanoby OpenAI
2025-04-14
openai/gpt-4.1-nano
Tiny GPT-4.1 option for classification, routing, and very high-volume tasks
- Context
- 1.04758M
- Input
- $0.1/M
- Output
- $0.4/M
GPT-4o miniby OpenAI
2024-07-18
openai/gpt-4o-mini
Small omni GPT for cheap multimodal assistance and production-scale traffic
- Context
- 128K
- Input
- $0.15/M
- Output
- $0.6/M
| Model | Creator | Raw benchmark score | Input types | Context | Input / Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| GPT-5openai/gpt-5 | OpenAI |
88.0 | 400K | $1.25 / $10 | 2025-08-07 | ||
| o3-proopenai/o3-pro | OpenAI |
84.9 | 200K | $20 / $80 | 2025-06-10 | ||
| Gemini 2.5 Progoogle/gemini-2.5-pro | Google |
83.1 | 1.04858M | $1.25 / $10 | 2025-06-17 | ||
| o3openai/o3 | OpenAI |
81.3 | 200K | $2 / $8 | 2025-04-16 | ||
| DeepSeek Reasonerdeepseek/deepseek-reasoner | DeepSeek |
74.2 | 1M | $0.14 / $0.28 | 2025-12-01 | ||
| Claude Opus 4 (latest)anthropic/claude-opus-4-0 | Anthropic |
72.0 | 200K | $15 / $75 | 2025-05-22 | ||
| Claude Opus 4anthropic/claude-opus-4-20250514 | Anthropic |
72.0 | 200K | $15 / $75 | 2025-05-22 | ||
| o4-miniopenai/o4-mini | OpenAI |
72.0 | 200K | $1.1 / $4.4 | 2025-04-16 | ||
| DeepSeek Chatdeepseek/deepseek-chat | DeepSeek |
70.2 | 1M | $0.14 / $0.28 | 2025-12-01 | ||
| Claude Sonnet 3.7anthropic/claude-3-7-sonnet-20250219 | Anthropic |
64.9 | 200K | $3 / $15 | 2025-02-19 | ||
| o1openai/o1 | OpenAI |
61.7 | 200K | $15 / $60 | 2024-12-05 | ||
| Claude Sonnet 4 (latest)anthropic/claude-sonnet-4-0 | Anthropic |
61.3 | 200K | $3 / $15 | 2025-05-22 | ||
| Claude Sonnet 4anthropic/claude-sonnet-4-20250514 | Anthropic |
61.3 | 200K | $3 / $15 | 2025-05-22 | ||
| o3-miniopenai/o3-mini | OpenAI |
60.4 | 200K | $1.1 / $4.4 | 2024-12-20 | ||
| Qwen3 235B-A22Balibaba/qwen3-235b-a22b | Alibaba Qwen |
59.6 | 131.072K | $0.7 / $2.8 | 2025-04 | ||
| DeepSeek-R1deepseek/deepseek-r1 | DeepSeek |
56.9 | 128K | $0.7 / $2.5 | 2025-01-20 | ||
| Gemini 2.5 Flashgoogle/gemini-2.5-flash | Google |
55.1 | 1.04858M | $0.3 / $2.5 | 2025-06-17 | ||
| GPT-4.1openai/gpt-4.1 | OpenAI |
52.4 | 1.04758M | $2 / $8 | 2025-04-14 | ||
| Claude Sonnet 3.5 v2anthropic/claude-3-5-sonnet-20241022 | Anthropic |
51.6 | 200K | $3 / $15 | 2024-10-22 | ||
| Qwen3 32Balibaba/qwen3-32b | Alibaba Qwen |
40.0 | 131.072K | $0.7 / $2.8 | 2025-04 | ||
| GPT-4.1 miniopenai/gpt-4.1-mini | OpenAI |
32.4 | 1.04758M | $0.4 / $1.6 | 2025-04-14 | ||
| Claude Haiku 3.5anthropic/claude-3-5-haiku-20241022 | Anthropic |
28.0 | 200K | $0.8 / $4 | 2024-10-22 | ||
| GPT-4oopenai/gpt-4o | OpenAI |
23.1 | 128K | $2.5 / $10 | 2024-05-13 | ||
| GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06 | OpenAI |
23.1 | 128K | $2.5 / $10 | 2024-08-06 | ||
| Qwen Maxalibaba/qwen-max | Alibaba Qwen |
21.8 | 32.768K | $1.6 / $6.4 | 2024-04-03 | ||
| GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20 | OpenAI |
18.2 | 128K | $2.5 / $10 | 2024-11-20 | ||
| Llama 4 Maverick 17B Instructmeta/llama-4-maverick-17b-instruct | Meta |
15.6 | 1M | $0.124 / $0.603 | 2025-04-05 | ||
| Command Acohere/command-a-03-2025 | Cohere |
12.0 | 256K | $2.5 / $10 | 2025-03-13 | ||
| Codestral (latest)mistral/codestral-latest | Mistral AI |
11.1 | 256K | $0.3 / $0.9 | 2024-05-29 | ||
| GPT-4.1 nanoopenai/gpt-4.1-nano | OpenAI |
8.9 | 1.04758M | $0.1 / $0.4 | 2025-04-14 | ||
| GPT-4o miniopenai/gpt-4o-mini | OpenAI |
3.6 | 128K | $0.15 / $0.6 | 2024-07-18 |