Compare AI models
| Specifications | ||
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 128k | 400k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $1.25 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $10.00 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.125 |
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | — | $1.25Azure |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $10.00Azure |
| — | $750OpenAI list price | |
| Benchmarks | ||
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 83.48% | 94.6% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 76.26% | 85.7% |
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 21% |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | — | 74.9% |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 75% | — |
Aider Polyglot (diff)Coding — editing code in six languages using the diff edit format | — | 88% |
τ²-bench · retailAgentic tasks — task success in the retail domain of the second-generation customer-service evaluation | — | 81.1% |
τ²-bench · airlineAgentic tasks — task success in the airline domain of the second-generation customer-service evaluation | — | 62.6% |
τ²-bench · telecomAgentic tasks — task success in the telecom domain of the second-generation customer-service evaluation | — | 96.7% |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | — | 24.8% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 91.82% | — |
HealthBench · hardHealthcare — physician rubric score on the hard subset of the original HealthBench evaluation | — | 46.2% |
CharXiv Reasoning · with toolsChart reasoning — The same chart-and-figure reasoning test, run with the AI allowed to use tools — writing code to inspect the image, for instance — rather than reading the chart unaided. Scores run higher than the unaided version, so read the two as separate tests. Higher is better. | — | 81.1% |
MMMU-Pro · standard and vision meanMultimodal reasoning — average across the standard and vision sets | — | 78.4% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 84.2% |
GraphWalks BFS (<128K)Long context — breadth-first traversal accuracy for inputs shorter than 128K tokens | — | 78.3% |
GraphWalks parents (<128K)Long context — parent-node retrieval accuracy for inputs shorter than 128K tokens | — | 73.3% |
OpenAI MRCR (2 needles) · 128KLong context — retrieval of two matching turns in the original MRCR evaluation | — | 95.2% |
OpenAI MRCR (2 needles) · 256KLong context — retrieval of two matching turns in the original MRCR evaluation | — | 86.8% |
| Overview | ||
| Company | Mistral | OpenAI |
| Release date | Sep 17 2025 | Aug 7 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Magistral Medium 1.2vsClaude Fable 5.2GPT-5vsClaude Fable 5.2Magistral Medium 1.2vsGemini 4 HydrogenGPT-5vsGemini 4 HydrogenMagistral Medium 1.2vsMuse EmberGPT-5vsMuse EmberMagistral Medium 1.2vsGrok 4.7GPT-5vsGrok 4.7Magistral Medium 1.2vsDeepSeek-V4.1-Flash-1017GPT-5vsDeepSeek-V4.1-Flash-1017Magistral Medium 1.2vsKimi K3.1 ProGPT-5vsKimi K3.1 ProFrequently asked questions
GPT-5 leads Magistral Medium 1.2 on 2 of the 2 benchmarks they both report (AIME 2025, GPQA Diamond). Only GPT-5 has a verified first-party price for an available API: $1.25 per million input tokens and $10.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Magistral Medium 1.2. GPT-5 shipped 41 days before Magistral Medium 1.2, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Magistral Medium 1.2) vs 400k (GPT-5).
On AIME 2025, GPT-5 leads at 94.6% vs Magistral Medium 1.2 at 83.48%. On GPQA Diamond, GPT-5 leads at 85.7% vs Magistral Medium 1.2 at 76.26%.