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. | 1M | — |
| 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. | $3.00 | $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. | $15.00 | $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. | $0.15 | $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. | $1.50Google AI Studio | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $7.50Google AI Studio | — |
| $1,350Google list price | $375SpaceXSI list price | |
| These models have no shared benchmark scores. | ||
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% |
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. | — | 76.7% |
SWE-sweepAgentic coding — subtask-weighted reward for software engineering with the mini-swe-agent harness | 12.8% | — |
FrontierCode 2.0Agentic coding — whether a model’s code changes to open-source repositories would be merged by their maintainers (version 2.0); separate from FrontierCode v1.1 scores | 46.2% | — |
Terminal-Bench-Science 0.1Agentic scientific computing — The same command-line setup as Terminal-Bench, pointed at scientific work: the AI has to drive research tooling and computational workflows through to a result, rather than administer a machine. Version 0.1 is the first release of the task set, and scores run lower than on the general board. Higher is better. | 70.5% | — |
RiemannBenchAdvanced mathematics — mathematical problem-solving evaluation published by Surge | 84% | — |
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% |
SEC-bench Pro (JavaScript)Vulnerability discovery — pass@1 on the 183-task May 2026 JavaScript-engine split, averaged over three trials with the Antigravity harness | 90.5% | — |
AutomationBenchBusiness workflows — Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better. | 56.3% | — |
AA Intelligence Index v5.0.1Overall intelligence — Artificial Analysis’s version 5.0.1 composite across nine evaluations of knowledge work, coding, science, and general knowledge | 61 | — |
Vals Index v2.2Professional work — Vals AI composite evaluation of professional tasks, version 2.2 | 70.9% | — |
Vending-Bench 2 (USD)Business simulation — ending bank balance in US dollars in Andon Labs’ vending-business simulation; higher is better | 16843 | — |
Chartography · no toolsChart tasks — The same chart-centred test with no tools: the AI has to read each chart unaided. Scores run far lower than the with-tools version, so read the two as separate tests. Higher is better. | 73.5% | — |
LVBenchVideo understanding — Can the AI follow a very long video — up to an hour — and answer questions that need details from far apart in it? Higher is better. | 89% | — |
GraphWalks BFS (256K–1M)Long context — breadth-first search F1 on the 200 GraphWalks problems with 256K to 1M tokens of context | 95.2% | — |
| Overview | ||
| Company | SpaceXSI | |
| Release date | Nov 18 2026 | Feb 17 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Gemini 4 NeonvsClaude Fable 5.2Grok 4.20 BetavsClaude Fable 5.2Gemini 4 NeonvsGPT-6.2 AstraGrok 4.20 BetavsGPT-6.2 AstraGemini 4 NeonvsMuse EmberGrok 4.20 BetavsMuse EmberGemini 4 NeonvsDeepSeek-V4.1-Flash-1017Grok 4.20 BetavsDeepSeek-V4.1-Flash-1017Gemini 4 NeonvsMistral Large 4Grok 4.20 BetavsMistral Large 4Gemini 4 NeonvsKimi K3.1 ProGrok 4.20 BetavsKimi K3.1 ProFrequently asked questions
Gemini 4 Neon and Grok 4.20 Beta don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Grok 4.20 Beta is cheaper on both input and output: $1.25 vs $3.00 per million input tokens, and $2.50 vs $15.00 per million output tokens. Figures are base-tier rates. Grok 4.20 Beta shipped 274 days before Gemini 4 Neon, 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.
Direct benchmark comparisons are unavailable — Gemini 4 Neon and Grok 4.20 Beta don't publish scores on any of the same benchmarks.