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 | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $3.00 | — |
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 | — |
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 | — |
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 | — | |
| These models have no shared benchmark scores. | ||
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% | — |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | — | 85.7% |
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% | — |
MATHReasoning — accuracy on the original competition mathematics test set | — | 73% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 72% |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | — | 86.2% |
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% | — |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | — | 68.1% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 63.2% |
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 | Aug 13 2024 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Gemini 4 NeonvsClaude Fable 5.2Grok‑2 minivsClaude Fable 5.2Gemini 4 NeonvsGPT-6.2 AstraGrok‑2 minivsGPT-6.2 AstraGemini 4 NeonvsMuse EmberGrok‑2 minivsMuse EmberGemini 4 NeonvsDeepSeek-V4.1-Flash-1017Grok‑2 minivsDeepSeek-V4.1-Flash-1017Gemini 4 NeonvsMistral Large 4Grok‑2 minivsMistral Large 4Gemini 4 NeonvsKimi K3.1 ProGrok‑2 minivsKimi K3.1 ProFrequently asked questions
Gemini 4 Neon and Grok‑2 mini don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Gemini 4 Neon has a verified first-party price for an available API: $3.00 per million input tokens and $15.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Grok‑2 mini. Grok‑2 mini shipped 827 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‑2 mini don't publish scores on any of the same benchmarks.