Understand the numbers

The value frontier

Every model, plotted by what it costs against how good it is. The staircase is the frontier: for those models, no other model scores at least as high, costs no more, and wins on one of the two. Everything below and to the right has such a model on the staircase, though not always a like-for-like replacement.

Changing the workload below moves the frontier less than you would expect: 50% of frontier models are on it under every workload (6 move). What does change is the price — the same model swings up to 3.6× across these shapes. So the control is not about which models to consider. It is about what you would actually pay for them.

Workload
Measured on

General · Balanced

Claude Opus 5.5

Anthropic

on the frontier
General capability
1514.8
Effective $/M
$8.00/M

Compared with the previous price rung, Gemini 3.8 Flash: +15.8 Elo · +$5.00/M for Balanced. Score differences are not task-success or capability guarantees.

Compare General scores and capabilities
$0.030$0.100$0.300$1.00$3.00$10.00$30.0010801170126013501440effective $ per million tokens — log scaleGeneral capability
effective $ per million tokens — log scale · General capability

On the frontier

General · Balanced · Effective $/M

  1. 1 Llama 3.1 8B Instruct Meta 1186.6 $0.025/M cheapest rung
  2. 2 gpt-oss-20b OpenAI 1287.4 $0.036/M +100.8 Elo · +$0.011/M vs previous rung
  3. 3 gpt-oss-120b OpenAI 1365.4 $0.060/M +78.0 Elo · +$0.024/M vs previous rung
  4. 4 DeepSeek V4 Flash 0423 DeepSeek 1432.1 $0.113/MPrice under confirmation since Oct 12, 2026 +66.7 Elo · +$0.053/M vs previous rung
  5. 5 Gemma 4 26B A4B Google 1434.2 $0.127/MPrice under confirmation since Oct 12, 2026 +2.1 Elo · +$0.014/M vs previous rung
  6. 6 MiMo-V2.6-Flash Xiaomi 1455.2 $0.175/MPrice under confirmation since Oct 12, 2026 +21.0 Elo · +$0.048/M vs previous rung
  7. 7 DeepSeek V4.1 Flash DeepSeek 1462.4 $0.182/MPrice under confirmation since Oct 12, 2026 +7.2 Elo · +$0.0073/M vs previous rung
  8. 8 GLM 5.3 Flash Z.ai 1471.1 $0.238/MPrice under confirmation since Oct 12, 2026 +8.7 Elo · +$0.055/M vs previous rung
  9. 9 MiMo-V2.6-Pro Xiaomi 1491.7 $0.540/M +20.6 Elo · +$0.303/M vs previous rung
  10. 10 Gemini 3.8 Flash Google 1499.0 $3.00/M +7.3 Elo · +$2.46/M vs previous rung
  11. 11 Claude Opus 5.5 Anthropic 1514.8 $8.00/M +15.8 Elo · +$5.00/M vs previous rung

Cite this claim

Plain text and BibTeX
Plain
132 of 143 rated, priced models have an alternative with an equal-or-higher measured score and an equal-or-lower price, with a strict advantage on at least one axis. 11 are not dominated on these two axes. As of 2026-10-13. Lens: LMArena Elo (CC BY 4.0). Ranking source digest: 8199366e23065fc6. https://undominated.ai/frontier/
Publication: sha256:7f43bf1ba022be9bb0d9d5462e7815de12aa148353b947efac4756084700b179; calculation SHA-256: 2be71186e159799b8a18bc0ae29953e6e0b7ab863bc824228f9f7201f785c716; permitted inputs: https://undominated.ai/data/publications/manifests/7f43bf1ba022be9bb0d9d5462e7815de12aa148353b947efac4756084700b179.json
BibTeX
@misc{undominated-dominated-census-2026-10-13,
  author = {{Undominated.ai}},
  title  = {Dominated census — Undominated.ai},
  year   = {2026},
  url    = {https://undominated.ai/frontier/},
  note   = {as of 2026-10-13; LMArena Elo (CC BY 4.0); ranking source 8199366e23065fc6},
  annote = {Publication: sha256:7f43bf1ba022be9bb0d9d5462e7815de12aa148353b947efac4756084700b179; calculation SHA-256: 2be71186e159799b8a18bc0ae29953e6e0b7ab863bc824228f9f7201f785c716; permitted inputs: https://undominated.ai/data/publications/manifests/7f43bf1ba022be9bb0d9d5462e7815de12aa148353b947efac4756084700b179.json}
}

LMArena scores used under CC BY 4.0 · numbers recomputed from the catalogue on this page. Input identity & calculation SHA.

Evidence & Ask