Leaderboard · 2026-10-28
The best LLMs in 2026
An LLM leaderboard built on real usage. Every model here is ranked by the tokens it actually processed on public AI gateways — the closest thing to a revealed preference for which models are worth running in production.
How "best" is measured in October 2026
50 models carried measurable traffic on the latest archived day, together moving about 28T tokens across 13 labs. Rather than scoring models on test sets, this page reads three signals off that traffic: raw share (who wins the most tokens), 30-day momentum (who is being adopted), and usage per dollar of list price (who is worth the money).
The current leader is DeepSeek: DeepSeek V4.1 Flash 1017 at 24.79% of tracked tokens, +21.07pp over 30 days. Because each day is archived, every change figure compares two real days rather than a rolling estimate.
Top 25 LLMs by real usage
Share of gateway tokens on the latest archived day.
Best value: usage per dollar
Token share divided by output list price per million.
| Model | Share % | $/M out | Value |
|---|---|---|---|
| Z.ai: GLM 5.3 Flash | 8.26 | $0.074 | 111.26 |
| DeepSeek: DeepSeek V4.1 Flash 1017 | 24.79 | $0.60 | 41.31 |
| DeepSeek: DeepSeek V4.1 Flash | 8.28 | $0.50 | 16.56 |
| OpenAI: GPT-6 Luna | 4.92 | $0.50 | 9.85 |
| DeepSeek: DeepSeek V4 Flash 0731 | 1.96 | $0.24 | 8.25 |
| DeepSeek: DeepSeek V4 Flash 0423 | 1.49 | $0.18 | 8.21 |
| Meta: Muse Spark 1.3 Contributor | 1.33 | $0.20 | 6.64 |
| Xiaomi: MiMo-V2.6-Flash | 1.52 | $0.28 | 5.41 |
Biggest movers over 30 days
Change in share of gateway tokens, percentage points.
| Model | Lab | Share % | 30d Δ |
|---|---|---|---|
| DeepSeek: DeepSeek V4.1 Flash 1017 | DeepSeek | 24.79 | +21.07pp |
| Z.ai: GLM 5.3 Flash | Z-AI | 8.26 | +2.75pp |
| MiniMax: MiniMax M3.1 Flash | MiniMax | 3.05 | +2.56pp |
| Anthropic: Claude Opus 5.5 | Anthropic | 3.44 | +2.09pp |
| OpenAI: GPT-6 Luna | OpenAI | 4.92 | +1.59pp |
| OpenAI: GPT-6.1 Sol | OpenAI | 1.80 | +1.37pp |
Best open-weight models
Open-weight releases now hold a meaningful slice of gateway traffic. The leaders by measured usage are DeepSeek: DeepSeek V4.1 Flash 1017, DeepSeek: DeepSeek V4.1 Flash, Z.ai: GLM 5.3 Flash. The open-weights index tracks that share over time.
Best LLMs in 2026 FAQ
- What is the best LLM in 2026?
- By the only measure that is not self-reported — how much real traffic a model carries — DeepSeek: DeepSeek V4.1 Flash 1017 from DeepSeek leads in October 2026 with 24.79% of tokens routed through the public AI gateways Tidelines tracks.
- Which LLMs are developers actually using in 2026?
- The current top three by measured token volume are DeepSeek: DeepSeek V4.1 Flash 1017, DeepSeek: DeepSeek V4.1 Flash, Z.ai: GLM 5.3 Flash. In total 50 models registered real traffic on 2026-10-28, but usage is heavily concentrated in the top ten.
- Which LLM gives the best value for money?
- Z.ai: GLM 5.3 Flash (Z-AI) currently has the strongest usage-per-dollar profile: 8.26% of tracked tokens at $0.074 per million output tokens.
- Which model is growing fastest?
- DeepSeek: DeepSeek V4.1 Flash 1017 has gained the most share over the last 30 days, at +21.07pp.
- Is this a benchmark leaderboard?
- No. Benchmarks measure how a model scores on test sets. This page measures what developers pay for and route production traffic to, computed daily from public gateway token counts.