Search Intent · best llm for rag
Best LLM for RAG in 2026
Context window and input list price first. For stuffing corpora, not for coding agents.
Weights:Context 40%In $ 25%Elo 20%TTFT 15%
Current #1 Ranked PickScore 82.8 / 100
GPT-5.6 Luna
OpenAI · Closed flagship
Context: 1.1M (Top 5%)In $: $0.1/1M (Top 19%)Elo: 1,466 (Top 51%)TTFT: 88 ms (Top 2%)
SWE-bench: 61.8%Elo: 1,466
View full model fact sheetComplete Ranked Category List
Models ranked by verified benchmark weights across SWE-bench and coding preference evaluations.
Score 82.8
Context: 1.1M (Top5%)In $: $0.1/1M (Top19%)Elo: 1,466 (Top51%)TTFT: 88 ms (Top2%)
🏆 #1 Overall Leader
Score 81.6
Context: 1.3M (Top2%)In $: $0.14/1M (Top25%)Elo: 1,490 (Top38%)TTFT: 165 ms (Top25%)
Rank #2vs #1
Score 78.6
Context: 1.3M (Top2%)In $: $0.1/1M (Top19%)Elo: 1,412 (Top69%)TTFT: 130 ms (Top14%)
Rank #3vs #1
Score 78.3
Context: 1M (Top13%)In $: $0.375/1M (Top47%)Elo: 1,530 (Top23%)TTFT: 82 ms (Top1%)
Rank #4vs #1
Score 74.6
Context: 1M (Top13%)In $: $0.1/1M (Top21%)Elo: 1,490 (Top38%)TTFT: 220 ms (Top49%)
Rank #5vs #1
Score 74.3
Context: 1M (Top13%)In $: $0.5/1M (Top52%)Elo: 1,495 (Top33%)TTFT: 95 ms (Top6%)
Rank #6vs #1
Score 73.8
Context: 1.1M (Top5%)In $: $1/1M (Top68%)Elo: 1,548 (Top19%)TTFT: 160 ms (Top23%)
Rank #7vs #1
Score 73.0
Context: 1M (Top13%)In $: $0.2/1M (Top32%)Elo: 1,468 (Top49%)TTFT: 170 ms (Top27%)
Rank #8vs #1
Score 72.8
Context: 2M (Top1%)In $: $1.25/1M (Top74%)Elo: 1,570 (Top9%)TTFT: 205 ms (Top43%)
Rank #9vs #1
Score 72.8
Context: 1M (Top13%)In $: $0.75/1M (Top61%)Elo: 1,506 (Top31%)TTFT: 92 ms (Top4%)
Rank #10vs #1
Score 71.2
Context: 2M (Top1%)In $: $0.2/1M (Top33%)Elo: 1,420 (Top67%)TTFT: 210 ms (Top45%)
Rank #11vs #1
Score 70.4
Context: 2M (Top1%)In $: $1.25/1M (Top74%)Elo: 1,552 (Top17%)TTFT: 220 ms (Top49%)
Rank #12vs #1
Frequently asked questions
Plain-English methodology and leaderboard answers
- GPT-5.6 Luna is the current #1 on this list. Rankings move when daily ingest updates SWE-bench, Elo, price, or latency.