Who's fastest, and what it costs to run them.
As of Nov 3, 2026, Opus 5.5 leads the Model Standings at 58, 2 points clear of Sonnet 5.5. Haiku 5.5 gives the most score per dollar, at $0.10 in and $0.50 out per million tokens. Most used this week: DeepSeek V4.1 Flash, with 34% of OpenRouter tokens and 11% on Vercel AI Gateway. 14 LLMs from 8 labs; 3 not yet scored.
- Biggest move on OpenRouter since the day before: DeepSeek V4.1 Flash, 33.1% → 34.4% of tokens.
- Biggest move on Vercel AI Gateway since the day before: Grok 4.7, 4.5% → 4.8% of tokens.
- GPT-6.1 Sol grew its OpenRouter share 26% week on week: 1.6% → 2.0%.
- Busiest model on OpenRouter that is not on our grid: Hy4 preview (Tencent), 4.6% of tokens.
- 2 new models with real traffic listed on OpenRouter or Vercel this week.
- GLM 5.3 FlashX LegalZ.ai · OpenRouter · Vercel · listed Nov 2
- Particle-1Particle AI · OpenRouter · Vercel · listed Oct 28
| Pos | Model | Score | Gap | $ in / out | Laps | Test lap |
|---|---|---|---|---|---|---|
| P1 | Opus 5.5TrackAnthropic | Leader | $4 / $20 | 3.3%▼5.4%▼ | Track | |
| P2 | Sonnet 5.5TrafficAnthropic | −2 | $2 / $10 | 1.3%▼2.1%▼ | Traffic | |
| P3 | Gemini 4 ArgonGoogle | −5 | $2 / $10 | 0.6%▲– | – | |
| P4 | Fable 5.1Anthropic | −5 | $10 / $50 | 0.0%▼– | – | |
| P5 | GPT-6 AstraOpenAI | −5 | $10 / $50 | 0.2%▼– | – | |
| P6 | GPT-6.1 SolOpenAI | −6 | $2 / $10 | 2.0%▲– | – | |
| P7 | Grok 4.7xAI | −12 | $2 / $6 | 0.0%▼4.8%▲ | – | |
| P8 | GLM-5.3Zhipu | −13 | $1.40 / $4.40 | 1.8%▼6.9%▼ | – | |
| P9 | Kimi K3Moonshot | −14 | $3 / $15 | 0.9%▼– | – | |
| P10 | Haiku 5.5TrackAnthropic | −15 | $0.10 / $0.50* | 1.4%▼– | Track | |
| P11 | GPT-6 LunaOpenAI | −20 | $0.10 / $0.50 | 4.5%▼4.8%▼ | – | |
| NC | V4.1 FlashDeepSeek | $0.30 / $1.20* | 34%▲11%▼ | – | ||
| NC | Gemini 3.8 FlashGoogle | $0.75 / $3.75 | 0.8%▼– | – | ||
| NC | Muse Spark 1.3Meta | $1.25 / $4.25 | 0.0%– | – |
In the news this week.
Headlines from the labs' own news pages and the two gateways' launch notes, in the seven days to Nov 3, 2026. Their words, linked to the source; we only pick which ones.
- Google DeepMindAgentic cheminformatics with Google Antigravity
- OpenAIAccelerating engineering for the physical world
- OpenAIHow Cisco defends at machine speed with OpenAI
- OpenAIHeimstaden is changing residential real estate management with AI
- VercelTencent Hy4 now available on AI Gateway
- VercelLongCat 2.5 now available on AI Gateway
- Google DeepMindSpeeding up planning decisions with AI
- OpenRouterGuardrails Now Separate Organization Limits from Workspace Defaults
- VercelLing 3.1 Flash 1019 now available on AI Gateway for free
- Google DeepMindGemini 4 Carbon: Our next frontier model
- OpenRouterHow we rebuilt provider routing for better, faster inference
Smarter costs more. Not always.
Score against blended list price, on a log scale. The line joins the models nothing else beats on both: every model off the line has a rival at least as smart for less. Hover or tap a dot for its numbers. Unscored models sit this one out.
scroll the chart sideways
Score is the Artificial Analysis Intelligence Index, taken from their public results and compared only within the same index version. Price is list, in US dollars per million tokens, input / output; open-weight prices are the first-party API, and hosts on OpenRouter often go lower. Blended price weighs input three to one, the shape of a typical agent turn. Laps is each model's share of all tokens over the last seven days on OpenRouter and on Vercel AI Gateway, two different crowds of developers; the arrow compares it with the seven days before, and a dash means too small to call. Source: OpenRouter (openrouter.ai/rankings), as of Nov 4, 2026. Licensed under CC BY 4.0. Source: Vercel AI Gateway usage data, as of Nov 3, 2026. Licensed under CC BY 4.0.
A verdict from putting the model on real work for a while, not a benchmark. Track means we would send real work to it today. Traffic means fine, nothing special. Pit lane means not ready. Most models have not had a lap yet.
Timing by sleds, which routes work across every lab and favours none. The board updates every morning, and every day keeps its own page, so a link to a day always shows that day. Quote it freely with a link back. The numbers behind it are open too, as JSON.
Past days.
Every day's board is kept as it stood, with that day's notes and headlines. Pick a day to see who led and what moved.