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. | 400k | — |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $0.05 | $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. | $0.40 | $2.50 |
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. | $0.005 | $0.20 |
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. | $0.025OpenAI | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.20OpenAI | — |
| $30.00OpenAI list price | $375SpaceXSI list price | |
| Benchmarks | ||
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. | 54.7% | 76.7% |
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. | — | 56% |
Aider Polyglot (diff)Coding — editing code in six languages using the diff edit format | 48.4% | — |
τ²-bench · retailAgentic tasks — task success in the retail domain of the second-generation customer-service evaluation | 62.3% | — |
τ²-bench · airlineAgentic tasks — task success in the airline domain of the second-generation customer-service evaluation | 41% | — |
τ²-bench · telecomAgentic tasks — task success in the telecom domain of the second-generation customer-service evaluation | 35.5% | — |
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. | 8.7% | — |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | — | 53.3% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 85.2% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 71.2% | — |
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. | 62.7% | — |
MMMU-Pro · standard and vision meanMultimodal reasoning — average across the standard and vision sets | 62.6% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 75.6% | — |
GraphWalks BFS (<128K)Long context — breadth-first traversal accuracy for inputs shorter than 128K tokens | 64% | — |
GraphWalks parents (<128K)Long context — parent-node retrieval accuracy for inputs shorter than 128K tokens | 43.8% | — |
OpenAI MRCR (2 needles) · 128KLong context — retrieval of two matching turns in the original MRCR evaluation | 43.2% | — |
OpenAI MRCR (2 needles) · 256KLong context — retrieval of two matching turns in the original MRCR evaluation | 34.9% | — |
| Overview | ||
| Company | OpenAI | SpaceXSI |
| Release date | Aug 7 2025 | Feb 17 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
GPT-5 nanovsClaude Fable 5.2Grok 4.20 BetavsClaude Fable 5.2GPT-5 nanovsGemini 4 CarbonGrok 4.20 BetavsGemini 4 CarbonGPT-5 nanovsMuse EmberGrok 4.20 BetavsMuse EmberGPT-5 nanovsDeepSeek-V4.1-Flash-1017Grok 4.20 BetavsDeepSeek-V4.1-Flash-1017GPT-5 nanovsMistral Large 4Grok 4.20 BetavsMistral Large 4GPT-5 nanovsKimi K3.1 ProGrok 4.20 BetavsKimi K3.1 ProFrequently asked questions
Grok 4.20 Beta leads GPT-5 nano on 1 of the 1 benchmark they both report (SWE-Bench Verified). GPT-5 nano is cheaper on both input and output: $0.05 vs $1.25 per million input tokens, and $0.40 vs $2.50 per million output tokens. Figures are base-tier rates. GPT-5 nano shipped 194 days before Grok 4.20 Beta, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On SWE-Bench Verified, Grok 4.20 Beta leads at 76.7% vs GPT-5 nano at 54.7%.