Skip to content

LLM Pareto Frontier — price vs intelligence, updated monthly

Living report · updated monthly · last updated
Edition: 2026-10 (latest) · all editions: 2026-10 · 2026-09 · 2026-08 · 2026-07

A model is Pareto-efficient if no other model is both cheaper and smarter. This report plots the current flagship LLMs — the open-weight flagships (including every one we serve) and the closed models from Anthropic, OpenAI and Google — on output price 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.

$0$10$20$30$40$50 Output price, $ per 1M tokens 2530354045505560 AA Intelligence Index Claude Opus 5 GPT-5.6 Sol Claude Fable 5 Opus 4.8 GPT-5.5 Sonnet 5 GPT-5.4 Gemini 3.5 Flash GPT-6 Astra Claude Fable 5.1 Claude Opus 5.5 Claude Sonnet 5.5 GPT-6.1 Sol Kimi K3 Qwen3.8 Max GLM 5.2 MiniMax M3 Kimi K2.6 Kimi K2.7 DeepSeek V4 Flash GLM 5.3 GLM-5.3-Flash DeepSeek V4.1 Flash MiMo-V2.6-Pro MiMo-V2.6-Flash Kimi K3.1 Pro the top open model is 3 pointsoff the top score — at half the price Open weights Proprietary Pareto frontier

Reading left to right: MiMo-V2.6-Flash → GLM-5.3-Flash → MiMo-V2.6-Pro → Claude Sonnet 5.5 → Claude Opus 5.5.

  • Kimi K3.1 Pro is now plotted as open-weights (2026-11-05): index 55 at $2/$10 — #4 of everything AA tracks, 3 points off the leader — and Moonshot published the weights on November 4 — the day it had promised — under a license that permits commercial serving. It is the top open-weights score on the current index (v4.3.2), 9 points above the previous best (MiMo-V2.6-Pro, 46). It still sits one point under the frontier line, not on it: Claude Sonnet 5.5 scores 56 at the identical $10/M. It dominates Kimi K3 outright (44 at $15), GPT-6.1 Sol, GPT-5.4 and every closed model priced above it except the two Anthropic 5.5 points. Full analysis: Kimi K3.1 Pro: specs, benchmarks, pricing — since 2026-11-06 it is served in our Flagship Pool.
  • Three closed models join to keep the top of the chart honest: Claude Opus 5.5 (58, $4/$20), Claude Sonnet 5.5 (56, $2/$10) and GPT-6.1 Sol (52, $2/$10). Opus 5.5 is the new index leader and the new top of the frontier — at less than half the output price of GPT-6 Astra and Claude Fable 5.1 (53 at $50), which it dominates along with Claude Opus 5 and GPT-5.6 Sol. Sonnet 5.5 takes the step below it and dominates GPT-6.1 Sol at the same price. AA now marks Opus 5, GPT-5.6 Sol and Kimi K3 as superseded; they stay tracked for history.
  • The frontier reads MiMo-V2.6-Flash (38, $0.28) → GLM-5.3-Flash (42, $0.50) → MiMo-V2.6-Pro (46, $0.87) → Claude Sonnet 5.5 (56, $10) → Claude Opus 5.5 (58, $20). The closed half of the line collapsed from four points to two, both Anthropic’s; the open half is unchanged.
  • The open-vs-closed gap is 3 points on today’s chart (Kimi K3.1 Pro 55 vs Claude Opus 5.5 58) — it was 12 (MiMo-V2.6-Pro 46) until K3.1 Pro’s weights landed on 2026-11-04, the narrowest gap in this report’s history. The step from the best open model to the next closed one is now 1 point at the same output price (K3.1 Pro → Sonnet 5.5, both $10); before the weights it was 10 points for 11.5× the price (MiMo-V2.6-Pro $0.87 → Sonnet 5.5 $10).
  • The DeepSeek V4.1 Flash point now tracks the served 1017 build on its own AA page: 45 at $1.20/M, +6 at the same price — it matches GLM 5.3 at 3.7× less and Qwen3.8 Max at 5× less, and is still dominated only by MiMo-V2.6-Pro.
  • Every tracked model priced under $5 per million output tokens is open-weight. GLM-5.3-Flash still anchors the cheap end ($0.50, 42) and matches Claude Opus 4.8 at 50× less. GLM 5.3, Kimi K3.1 Pro, Qwen3.8 Max, DeepSeek V4.1 Flash and MiMo V2.6 Flash are served in our pools (Kimi K3.1 Pro in the Flagship Pool since 2026-11-06, replacing Kimi K3 in place); MiMo-V2.6-Pro and GLM-5.3-Flash are under evaluation (live status).
  • Scores on this chart are Intelligence Index v4.3.2 (since 2026-09-22): a harder composite than the v4.1.1 used through August, which rescored the whole field 12–19 points lower at unchanged prices. Scores from earlier editions are not comparable; compare positions, which is what the frontier is for.
ModelAA IndexInput $/MOutput $/MWeightsPareto-efficient
Claude Opus 5.558$4.00$20.00closed✓
Claude Sonnet 5.556$2.00$10.00closed✓
Kimi K3.1 Pro55$2.00$10.00opendominated by Claude Sonnet 5.5
GPT-6 Astra53$10.00$50.00closeddominated by Claude Opus 5.5
Claude Fable 5.153$10.00$50.00closeddominated by Claude Opus 5.5
GPT-6.1 Sol52$2.00$10.00closeddominated by Claude Sonnet 5.5
Claude Opus 551$5.00$25.00closeddominated by Claude Opus 5.5
Claude Fable 550$10.00$50.00closeddominated by Claude Opus 5.5
GPT-5.6 Sol47$4.00$20.00closeddominated by Claude Opus 5.5
MiMo-V2.6-Pro46$0.43$0.87open✓
DeepSeek V4.1 Flash45$0.30$1.20opendominated by MiMo-V2.6-Pro
GLM 5.345$1.40$4.40openmatched by DeepSeek V4.1 Flash at 3.7× less
Qwen3.8 Max45$2.00$6.00openmatched by DeepSeek V4.1 Flash at 5.0× less
Kimi K344$3.00$15.00opendominated by Claude Sonnet 5.5
GLM-5.3-Flash42$0.15$0.50open✓
Opus 4.842$5.00$25.00closedmatched by GLM-5.3-Flash at 50.0× less
GPT-5.439$2.50$15.00closeddominated by Claude Sonnet 5.5
MiMo-V2.6-Flash38$0.14$0.28open✓
Sonnet 538$2.00$10.00closedmatched by MiMo-V2.6-Flash at 35.7× less
GPT-5.538$5.00$30.00closedmatched by MiMo-V2.6-Flash at 107.1× less
DeepSeek V4 Flash34$0.14$0.28opendominated by MiMo-V2.6-Flash
GLM 5.234$1.40$4.40openmatched by DeepSeek V4 Flash at 15.7× less
Gemini 3.5 Flash33$1.50$9.00closeddominated by MiMo-V2.6-Pro
MiniMax M329$0.30$1.20opendominated by MiMo-V2.6-Pro
Kimi K2.627$0.95$4.00opendominated by MiMo-V2.6-Pro
Kimi K2.726$0.95$4.00opendominated by MiMo-V2.6-Pro

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.

$0.00$10$20$30$40$50 Output price, $ per 1M tokens 2530354045505560 AA Intelligence Index 2026-09 2026-10 (current) Current frontier Previous editions (older = fainter) Open Closed

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. Kimi K3.1 Pro was plotted as closed-weights from 2026-10-26 until Moonshot published the weights on 2026-11-04; its point and row flipped to open on 2026-11-05 with no number changed. Index points aren’t linear in value.

  • 2026-10 (updated 2026-11-05, no frontier change) — Kimi K3.1 Pro flips to open-weights: Moonshot published the weights on November 4 under the Kimi K3.1-Pro License (commercial serving permitted). No score or price moved and the frontier is unchanged — K3.1 Pro stays one point under Claude Sonnet 5.5 at the same $10/M — but the chart’s open-vs-closed gap drops from 12 points to 3, and the best open score on the current index goes from 46 (MiMo-V2.6-Pro) to 55. Still confirmed for our Flagship Pool, pending capacity validation.

  • 2026-10 (updated 2026-10-26) — Kimi K3.1 Pro joins the tracked set (55, $2/$10): Moonshot’s post-trained K3, #4 on the index and 3 points off the leader, plotted as closed until the weights announced for 2026-11-04 are published — it is confirmed for our Flagship Pool. Claude Opus 5.5 (58, $4/$20), Claude Sonnet 5.5 (56, $2/$10) and GPT-6.1 Sol (52, $2/$10) join as well: Opus 5.5 is the new index leader and the new top of the frontier; Sonnet 5.5 edges K3.1 Pro by a point at the same price and takes the step below; GPT-6 Astra, Claude Fable 5.1, Claude Opus 5 and GPT-5.6 Sol all leave the line, dominated. The DeepSeek V4.1 Flash point now follows the served 1017 build on its own AA page (45, +6 at the same price). Frontier: MiMo-V2.6-Flash → GLM-5.3-Flash → MiMo-V2.6-Pro → Claude Sonnet 5.5 → Claude Opus 5.5.

  • 2026-10 (updated 2026-10-18) — a quiet month for scores: every previously tracked model is unchanged in index. MiMo V2.6 Flash gets its Artificial Analysis entry, joins the tracked set (38, $0.14/$0.28, MIT weights) and enters the frontier as its new low-price anchor — nothing scored 38 or below comes close on price. Frontier: MiMo-V2.6-Flash → GLM-5.3-Flash → MiMo-V2.6-Pro → GPT-5.6 Sol → Claude Opus 5 → GPT-6 Astra → Claude Fable 5.1. AA also re-lists the retired DeepSeek V4 Flash at $0.14/$0.28 (was $0.44/$1.32). DeepSeek shipped V4.1-Flash-1017 on 2026-10-17 (what changed) — AA has not re-scored it, so the V4.1 Flash point still reflects the September build.

  • 2026-09-23 (no frontier change) — MiMo V2.6 Flash replaces MiMo V2.5 in our Core Pool in place, at the same $0.14/$0.28 list price: 309B MoE / 15B active, image input, MIT weights. Artificial Analysis has not scored it, so it stays on the watchlist and no point on this chart moves.

  • 2026-09 (2026-09-22) — AA moved its index to v4.3.2: every previously tracked score fell 12–19 points at unchanged prices — cross-edition drops at this date are methodology, not model changes. MiMo-V2.6-Pro joins the tracked set (46, $0.43/$0.87, MIT weights) as the #1 open-weights model and enters the frontier, dominating GLM 5.3, Kimi K3, Sonnet 5 and DeepSeek V4.1 Flash — GLM 5.3 leaves the line. DeepSeek V4.1 Flash is scored (39, $0.30/$1.20 peak) and joins the tracked set. GPT-6 Astra and Claude Fable 5.1 (both 53, $10/$50) join the tracked set as the new top of the index; Claude Fable 5 becomes dominated. Frontier: GLM-5.3-Flash → MiMo-V2.6-Pro → GPT-5.6 Sol → Claude Opus 5 → GPT-6 Astra / Claude Fable 5.1. Analysis: MiMo-V2.6 Pro & Flash.

  • 2026-09-10 (no frontier change) — DeepSeek V4.1 Flash ships and replaces V4 Flash in our Core Pool: 552B MoE (8B/16B active), causal encoder–decoder, native vision, MIT weights, $0.30/$1.20 peak list — cheaper than the model it replaces. Artificial Analysis has not scored it, so it is added to the watchlist and no point on this chart moves; the DeepSeek point stays V4 Flash until an independent index exists.

  • 2026-08 refresh (2026-08-31) — GLM-5.3-Flash joins the tracked set (57, $0.15/$0.50) and lands straight on the frontier: Z.ai’s 18B-active, MIT-licensed, natively multimodal MoE matches Claude Opus 4.8 at 50× less and dominates DeepSeek V4 Flash, MiniMax M3 and Kimi K2.7 — the frontier’s whole cheap half collapses into one point. Frontier: GLM-5.3-Flash → GLM 5.3 → GPT-5.6 Sol → Claude Opus 5. Analysis: GLM-5.3-Flash: specs, benchmarks & pricing.

  • 2026-08 refresh (2026-08-30) — GLM 5.3 joins the tracked set (60, $1.40/$4.40) two days after its open weights shipped under the GLM-5.3 License, and enters the frontier at once: it dominates Qwen3.8 Max, Sonnet 5 and GLM 5.2, and matches Kimi K3 at 3.4× less — K3 leaves the line. GPT-5.6 Sol’s output price drops $30 → $20 and it re-enters the frontier. Frontier: MiniMax M3 → DeepSeek V4 Flash → GLM 5.3 → GPT-5.6 Sol → Claude Opus 5. GLM 5.2 stays tracked for history; it was upgraded in place to 5.3 in our Frontier Pool.

  • 2026-08 refresh (2026-08-14) — three moves in one collection. AA recalibrated its index to v4.1.1: every tracked score shifted up 1–5 points at unchanged prices — cross-edition score jumps around this date are methodology, not model changes. Qwen3.8 Max joins the tracked set (58, $2/$6) now that its weights shipped — it enters the frontier and pushes Sonnet 5 off it, leaving Opus 5 as the only closed model on the line. And DeepSeek V4 Flash’s peak list pricing took effect ($0.14/$0.28 → $0.44/$1.32), bringing MiniMax M3 back onto the frontier. Frontier: MiniMax M3 → DeepSeek V4 Flash → GLM 5.2 → Qwen3.8 Max → Kimi K3 → Claude Opus 5.

  • 2026-08 (2026-08-01) — release-week update: the V4-Flash-0731 retrain lifts DeepSeek V4 Flash 40 → 50 at unchanged prices ($0.14/$0.28) — a 10-point single-model jump. It now matches Gemini 3.5 Flash at 32× lower output price and pushes MiniMax M3 off the frontier (dominated). Frontier: DeepSeek V4 Flash → GLM 5.2 → Sonnet 5 → Kimi K3 → Claude Opus 5.

  • 2026-07 refresh (2026-07-28) — release-week update: Kimi K3 (57, $3/$15), Claude Opus 5 (61, $5/$25) and GPT-5.6 Sol (59, $5/$30) added to the tracked set. K3 and Opus 5 enter the frontier; Fable 5 and Opus 4.8 leave it (both dominated by Opus 5). Sonnet 5’s output price dropped $15 → $10. The open-vs-closed gap is now 4 index points — the narrowest since GLM-5 (February).

  • 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.


GLM 5.3, Kimi K3.1 Pro, Qwen3.8 Max, Kimi K3, DeepSeek V4.1 Flash and MiMo V2.6 Flash are served flat-rate in our pools — Flagship from $169.15/mo, Frontier from $60.35/mo, Core from $18.70/mo — where the marginal token costs zero during your reserved hours. Kimi K3.1 Pro joined the Flagship Pool on 2026-11-06; MiMo-V2.6-Pro and GLM-5.3-Flash are under evaluation.