LLM Pareto Frontier — price vs intelligence, updated monthly
A model is Pareto-efficient if no other model is both cheaper and smarter. This report plots the current flagship LLMs — the open-weight models we serve and the closed models from Anthropic, OpenAI and Google — on output price (log scale) versus the Artificial Analysis Intelligence Index, and computes the frontier from the data. Everything below the line is dominated: a strictly better deal exists.
Method: all numbers come from the same source on the same day — Artificial Analysis model pages (Intelligence Index, vendor list prices). Each edition is archived so you can watch the frontier move over time.
Current frontier (edition 2026-07)
Section titled “Current frontier (edition 2026-07)”Reading left to right: DeepSeek V4 Flash → MiniMax M3 → GLM 5.2 → Sonnet 5 → Opus 4.8 → Claude Fable 5.
Analysis
Section titled “Analysis”- Below $15 per million output tokens, the entire Pareto frontier is open-weight — and all three models on it (DeepSeek V4 Flash, MiniMax M3, GLM 5.2) are in our pools.
- Every proprietary model on the frontier is Anthropic’s. GPT-5.5 is dominated by Claude Opus 4.8 (cheaper and smarter), GPT-5.4 is matched on intelligence and undercut 3.4× by GLM 5.2, and Gemini 3.5 Flash is beaten on both axes by GLM 5.2.
- The frontier goes near-vertical at the top: GLM 5.2 (51) → Fable 5 (60) buys 9 index points for 11.4× the output price.
The data
Section titled “The data”| Model | AA Index | Input $/M | Output $/M | Weights | Pareto-efficient |
|---|---|---|---|---|---|
| Claude Fable 5 | 60 | $10.00 | $50.00 | closed | ✓ |
| Opus 4.8 | 56 | $5.00 | $25.00 | closed | ✓ |
| GPT-5.5 | 55 | $5.00 | $30.00 | closed | dominated by Opus 4.8 |
| Sonnet 5 | 53 | $3.00 | $15.00 | closed | ✓ |
| GLM 5.2 | 51 | $1.40 | $4.40 | open | ✓ |
| GPT-5.4 | 51 | $2.50 | $15.00 | closed | matched by GLM 5.2 at 3.4× less |
| Gemini 3.5 Flash | 50 | $1.50 | $9.00 | closed | dominated by GLM 5.2 |
| MiniMax M3 | 44 | $0.30 | $1.20 | open | ✓ |
| Kimi K2.6 | 43 | $0.95 | $4.00 | open | dominated by MiniMax M3 |
| Kimi K2.7 | 42 | $0.95 | $4.00 | open | dominated by MiniMax M3 |
| DeepSeek V4 Flash | 40 | $0.14 | $0.28 | open | ✓ |
How the frontier moves
Section titled “How the frontier moves”Each edition’s frontier is archived; this chart overlays them, current on top. Over time it shows the defining dynamic of this market: the frontier sliding down (cheaper) and right-side-up (smarter) — driven almost entirely by open-weight releases.
One edition so far — previous frontiers will appear here as monthly editions accumulate.
Caveats
Section titled “Caveats”The Intelligence Index is one composite — task-specific rankings differ. Kimi K2.6 sits off-frontier here yet holds the best open SWE-bench Verified score (80.2); for agentic coding the ranking flips — see the Which-LLM guide for tier-fair matchups. Prices are vendor list prices for the reasoning variants Artificial Analysis evaluates; open-weight prices vary by host. MiMo V2.5, which we also serve, has no index entry yet and is excluded rather than estimated. Index points aren’t linear in value.
Changelog
Section titled “Changelog”- 2026-07 (first edition) — baseline. Frontier: DeepSeek V4 Flash, MiniMax M3, GLM 5.2, Sonnet 5, Opus 4.8, Fable 5. Notable context at launch: GLM 5.2 (released mid-June) is the top-scoring open-weights model in index history; AA’s v4.1 recalibration lowered scores across the board vs the April v4.0 figures.
The three sub-$15 frontier models are served flat-rate in our pools — Frontier from $44.20/mo, Core from $5.94/mo — where the marginal token costs zero during your reserved hours.