Coverage — planned vs landed

Every planned model × effort × arm, matched against landed data. Batches land incrementally — this board is the honest map of what exists and what is still a gap.

as of Jul 20, 2026, 4:07 PM
157/ 264
59%
landed · 59% of 264 planned
157
landed
1
partial
103
gap
3
paused
264
planned

742 valid slots collected

Chinese models: 27 official-API seats still unrun, 14 families with zero data so far.

This is the gap we most want closed. Every figure here is computed from the plan against landed data — never a hand-written count. Click any gap cell below to run it yourself with your own key.

17families planned27 / 36api seats open14zero-data families42 / 86cells with data
landedevery variant has ≥1 valid slotpartialsome valid slots, but not every variantattemptedconfig exists, zero valid slotsmissingno config yetpausedplanned but disabled in the matrix
show
claude-fable-5claude
claude-haiku-4-5claude
claude-opus-4-8claude
claude-sonnet-5claude
deepseek-v4-flashdeepseek
highmax
deepseek-v4-prodeepseek
highmax
doubao-seed-2-1-pro-260628doubao
disabledenabled
ernie-5.1ernie
gemini-3.1-progemini
gemini-3.5-flashgemini
minimallowmediumhigh
google/gemma-4-31b-itgemma
glm-5.2glm
gpt-5.2-codexgpt
lowmediumhighxhigh
gpt-5.4gpt
nonelowmediumhighxhigh
gpt-5.4-minigpt
nonelowmediumhigh
gpt-5.5gpt
high
gpt-5.6-lunagpt
gpt-5.6-solgpt
gpt-5.6-terragpt
grok-4.3grok
lowmediumhighdefault
grok-4.5grok
lowmediumhighdefault
hy3hunyuan
intern-s1-prointern
kwaipilot/kat-coder-pro-v2.5kat
kimi-k2.6kimi
offon
kimi-k2.7-codekimi
kimi-k3kimi
meta-llama/llama-4-maverickllama
LongCat-2.0longcat
mai-thinking-1mai
mercury-2mercury
mimo-v2.5-promimo
MiniMax-M3minimax
mistral-medium-2604mistral
nvidia/nemotron-3-ultra-550b-a55bnemotron
amazon/nova-2-lite-v1nova
allenai/olmo-3.1-32b-thinkolmo
openpangu-2.0-flashpangu
default
qwen3.7-maxqwen
inclusionai/ring-2.6-1tring
spark-xspark
step-3.7-flashstep
claude-fable-5claude
lowmediumhighxhighmax
claude-haiku-4-5claude
lowmediumhighxhighmax
claude-opus-4-8claude
lowmediumhighxhighmax
claude-sonnet-5claude
lowmediumhighxhighmax
gpt-5.6-solgpt
gpt-5.6-terragpt
gpt-5.4gpt
lowmediumhighxhigh
gpt-5.4-minigpt
lowmediumhigh
gpt-5.5gpt
lowmediumhighxhigh
gpt-5.6-lunagpt
lowmediumhighxhigh
gpt-5.6-solgpt
lowmediumhighxhigh
gpt-5.6-terragpt
lowmediumhighxhigh
glm-5.2glm
deepseek-v4-flashmulti
deepseek-v4-promulti
glm-5multi
glm-5.1multi
glm-5.2multi
grok-4.5multi
hy3-previewmulti
kimi-k2.5multi
kimi-k2.6multi
kimi-k2.7-codemulti
kimi-k3multi
mimo-v2-omnimulti
mimo-v2-promulti
mimo-v2.5multi
mimo-v2.5-promulti
minimax-m2.5multi
minimax-m2.7multi
minimax-m3multi
qwen3.5-plusmulti
qwen3.6-plusmulti
qwen3.7-maxmulti
qwen3.7-plusmulti
grok-4.5grok
lowmediumhigh
kimi-k3kimi
claude-haiku-4-5multi
claude-opus-4-5multi
claude-opus-4-6multi
lowmediumhighmax
claude-opus-4-7multi
lowmediumhighxhighmax
claude-opus-4-8multi
lowmediumhighxhighmax
claude-sonnet-4multi
claude-sonnet-4-5multi
claude-sonnet-4-6multi
lowmediumhighmax
claude-sonnet-5multi
lowmediumhighxhighmax
deepseek-v3.2multi
glm-5multi
gpt-5.6-lunamulti
lowmediumhighxhighmax
gpt-5.6-solmulti
lowmediumhighxhighmax
gpt-5.6-terramulti
lowmediumhighxhighmax
minimax-m2.1multi
minimax-m2.5multi
qwen3-coder-nextmulti
deepseek-v4-flashmulti
deepseek-v4-promulti
glm-5multi
glm-5.1multi
glm-5.2multi
grok-4.5multi
hy3-previewmulti
kimi-k2.5multi
kimi-k2.6multi
kimi-k2.7-codemulti
kimi-k3multi
mimo-v2-omnimulti
mimo-v2-promulti
mimo-v2.5multi
mimo-v2.5-promulti
minimax-m2.5multi
minimax-m2.7multi
minimax-m3multi
qwen3.5-plusmulti
qwen3.6-plusmulti
qwen3.7-maxmulti
qwen3.7-plusmulti
qwen3.7-maxqwen
Cost referencePer-call USD ranges observed while building this dataset. A config is N valid slots × 2 prompt variants.
familyarmper-call USDbasisnote
gptapi$0.05 – $2observedOfficial /responses, background mode. Averaged ~$0.45/call across effort tiers on gpt-5.4 / 5.4-mini / 5.2-codex; xhigh on full-size models reaches ~$2/call. gpt-5.6 family not yet measured, expected higher.
grokapi$0.02 – $0.12observedOfficial x.ai API: full grok-4.3 + grok-4.5 sweep (64 calls) cost ~$3.1 total.
claudeCC$0.01 – $0.6planClaude Code harness on a flat-rate plan; the metered-equivalent of our 4-model x 5-effort sweep was ~$64 (fable-5 alone ~$49). Zero marginal cost on plan.
claudeapi$0.05 – $1estimatedOfficial Anthropic API not yet run; range projected from Claude Code metered-equivalents.
gptcodex-oauthplan / freeplancodex CLI signed into a ChatGPT plan; zero marginal cost.
grokgrok-cliplan / freeplangrok CLI OAuth subscription; zero marginal cost.
multiopencodeplan / freeplanopencode go subscription (22 models, CLI harness + gateway api); zero marginal cost.
multigoplan / freeplanopencode go gateway api line, same subscription.
deepseekapi$0.001 – $0.03estimatedOfficial first-party API list price ballpark; not yet run.
qwenapi$0.002 – $0.05estimatedDashScope first-party list price ballpark; not yet run.
glmapi$0.002 – $0.05estimatedZhipu first-party list price ballpark; not yet run.
kimiapi$0.002 – $0.05estimatedMoonshot first-party list price ballpark; not yet run.
geminiapi$0.01 – $0.3estimatedNot yet run (deliberately deferred).

Observed ranges — they vary strongly with effort tier; treat as planning numbers, not quotes.

Click any missing or attempted cell to add it to a contribute batch.

Progress · weather-card-benchmark