The LLM market is too crowded to pick by brand memory. This page is a decision tool: every card says when to use a model, when to skip it and which data backs that call. Filter by use case, price and market position.
Updated 2026-08-02 · Next review by 2026-08-16 · What changed →
Choose what you need. The catalogue immediately narrows to models matching every selection.
Three quick choices without scrolling: one for the hardest work, one for cheap volume and one for teams that do not want to depend only on a closed API.
My read
coding pick backed by current AA.
Claude Opus 5 has IQ 60.7 and input $5/M in the sources. Consider it for coding, AI agents; for mass-volume, real-time-latency, run a second benchmark before rollout.
mid-budget · market frontier · verified by external data
When to pick itMy read
batch pick backed by current AA.
DeepSeek V4 Flash has IQ 40.3 and input $0.14/M in the sources. Consider it for large batches, fast replies; for deep-frontier-reasoning, top-coding, run a second benchmark before rollout.
open / self-run · specialist · verified by external data
When to pick itMy read
self-hosted pick backed by current AA.
GLM-5.2 has IQ 51.1 and input $1.4/M in the sources. Consider it for self-hosted stack, sensitive deployments; for premium-agents, top-coding, run a second benchmark before rollout.
open / self-run · specialist · verified by external data
When to pick itThis is the broader catalogue. Filters narrow it by situation; details keep hard numbers and sources out of the first read.
No model matches this combination. Try fewer filters.
My read
coding pick backed by current AA.
Claude Opus 5 has IQ 60.7 and input $5/M in the sources. Consider it for coding, AI agents; for mass-volume, real-time-latency, run a second benchmark before rollout.
mid-budget · market frontier · verified by external data
When to pick itMy read
coding pick backed by current AA.
Claude Fable 5 has IQ 59.9 and input $10/M in the sources. Consider it for coding, AI agents; for mass-volume, real-time-latency, run a second benchmark before rollout.
premium, when mistakes hurt · market frontier · verified by external data
When to pick itMy read
coding pick backed by current AA.
GPT-5.6 Sol has IQ 58.9 and input $5/M in the sources. Consider it for coding, AI agents; for self-hosted stack, real-time-latency, run a second benchmark before rollout.
mid-budget · market frontier · verified by external data
When to pick itMy read
coding pick backed by current AA.
Kimi K3 has IQ 57.1 and input $3/M in the sources. Consider it for coding, large batches; for enterprise-governance, tool-use, run a second benchmark before rollout.
mid-budget · market frontier · verified by external data
When to pick itMy read
coding pick backed by current AA.
Grok 4.5 has IQ 53.8 and input $2/M in the sources. Consider it for coding, fast replies; for self-hosted stack, sensitive deployments, run a second benchmark before rollout.
mid-budget · market frontier · verified by external data
When to pick itMy read
coding pick backed by current AA.
Claude Sonnet 5 has IQ 53.4 and input $2/M in the sources. Consider it for coding, AI agents; for self-hosted stack, mass-volume, run a second benchmark before rollout.
mid-budget · specialist · verified by external data
When to pick itMy read
self-hosted pick backed by current AA.
GLM-5.2 has IQ 51.1 and input $1.4/M in the sources. Consider it for self-hosted stack, sensitive deployments; for premium-agents, top-coding, run a second benchmark before rollout.
open / self-run · specialist · verified by external data
When to pick itMy read
batch pick backed by current AA.
DeepSeek V4 Flash has IQ 40.3 and input $0.14/M in the sources. Consider it for large batches, fast replies; for deep-frontier-reasoning, top-coding, run a second benchmark before rollout.
open / self-run · specialist · verified by external data
When to pick itMy read
batch pick backed by current AA.
DeepSeek V4 Pro has IQ 44.3 and input $0.435/M in the sources. Consider it for large batches, coding; for enterprise-governance, premium-agents, run a second benchmark before rollout.
open / self-run · specialist · verified by external data
When to pick itMy read
rag pick backed by current AA.
Command A Plus has IQ 22.5 and input $0/M in the sources. Consider it for company knowledge, document extraction; for top-coding, deep-frontier-reasoning, run a second benchmark before rollout.
cheap at volume · specialist · verified by external data
When to pick itMy read
batch pick backed by current AA.
Gemini 3.6 Flash has IQ 50.1 and input $1.5/M in the sources. Consider it for large batches, company knowledge; for deep-coding, real-time-latency, run a second benchmark before rollout.
mid-budget · specialist · verified by external data
When to pick itMy read
self-hosted pick backed by current AA.
Llama 4 Maverick has IQ 14.3 and input $0.27/M in the sources. Consider it for self-hosted stack, sensitive deployments; for managed-api-comfort, deep-frontier-reasoning, run a second benchmark before rollout.
open / self-run · specialist · verified by external data
When to pick itMy read
rag pick backed by current AA.
Gemini 3.1 Pro Preview has IQ 46.5 and input $2/M in the sources. Consider it for company knowledge, vision and multimodal; for real-time-latency, self-hosted stack, run a second benchmark before rollout.
mid-budget · specialist · verified by external data
When to pick itMy read
multilingual pick backed by current AA.
Qwen3.7 Max has IQ 46 and input $2.5/M in the sources. Consider it for multilingual content, coding; for self-hosted stack, premium-agents, run a second benchmark before rollout.
mid-budget · specialist · verified by external data
When to pick itMy read
compliance pick backed by current AA.
Mistral Medium 3.5 has IQ 29.9 and input $1.5/M in the sources. Consider it for sensitive deployments, company knowledge; for deep-frontier-reasoning, top-coding, run a second benchmark before rollout.
mid-budget · specialist · verified by external data
When to pick itMy read
compliance pick backed by current AA.
Mistral Large 3 has IQ 15.9 and input $0.5/M in the sources. Consider it for sensitive deployments, document extraction; for deep-frontier-reasoning, AI agents, run a second benchmark before rollout.
cheap at volume · specialist · verified by external data
When to pick itCurated decision snapshot, not a live leaderboard. Primary data comes from Artificial Analysis, with LMArena, LLM Stats, Aider, SWE-Bench, DeepSWE and HF Open LLM Leaderboard used when available during the run. The page is reviewed roughly every two weeks and cards without data show a loading state instead of invented numbers.
