Radar · latest confirmed releases

3 source-linked updates

Free Radar Brief ranks up to five confirmed market changes and keeps the original source attached. No card required.

See the free Radar Brief Browse public updates

Latest

GPT-6 Astra released

OpenAI · Sep 3, 2026

Source confirmed

Gemini 3.8 Flash and Gemini 3.8 Flash Cyber released

Google · Sep 2, 2026

Muse Spark 1.3 released

Meta · Sep 2, 2026

Decision-ready picks

Current models that clear the ranking, freshness, and evidence thresholds for each decision.

Qualification method

DecisionModelCurrent measureProvenance

Best open weightHighest-scoring evidence-qualified current open-weight model.Qwen3.8 MaxAlibaba72.43overall scoreSupported · 3 source families
Best near-frontier value95% of the leading score at a lower output price.Gemini 3.8 FlashGoogle$3.75output / 1M tokensSupported · 2 source families
Fastest measuredFastest externally measured model that also clears the ranking and evidence thresholds.LFM2.5-2.6BLiquidAI595tokens / secArtificial Analysis · updated 2026-09-04
Largest useful contextLargest context among evidence-qualified current models retaining at least half of the leading score.Grok 4.20xAI2Mcontext windowSupported · 2 source families

Qualification method

The LLM leaderboard — September 2026 rankings

Benchmarks, pricing, runtime signals, and context window in one table. Filter state syncs to the URL so every view is shareable. Supported and Estimated labels show how much independent evidence backs each position.

Methodology Providers AI Race

CSV JSON

AG AgenticCO CodingRE ReasoningMM Multimodal & GroundedKN KnowledgeML MultilingualIF Instruction FollowingMA Math

LLM leaderboard table

1 Claude Fable 5.1 AnthropicSupported	Anthropic	Closed	Current	Reasoning	1M	$10.00 / $50.00	66	282.34s	82.95	79	84	79	—	86	—	—	—	1504.21
2 GPT-6 Astra OpenAIEstimated	OpenAI	Closed	Current	Reasoning	1.05M	$10.00 / $50.00	Not measured	Not measured	81.05	70	75	89	83	82	—	—	85	—
3 Claude Fable 5 AnthropicSupported	Anthropic	Closed	Superseded	Reasoning	1M+	$10.00 / $50.00	70	108.02s	80.91	75	77	76	62	84	—	78	—	1507.16
4 Claude Opus 5 AnthropicSupported	Anthropic	Closed	Current	Reasoning	—	$5.00 / $25.00	57	85.93s	80.67	77	76	76	88	82	—	—	—	1493.33
5 GPT-5.6 Sol OpenAISupported	OpenAI	Closed	Superseded	Reasoning	1.05M	$5.00 / $30.00	77	107.13s	79.65	70	74	70	86	80	—	89	97	1483.15
6 Gemini 3.8 Flash GoogleSupported	Google	Closed	Current	Reasoning	1M	$0.75 / $3.75	327	10.75s	78.41	68	68	79	83	76	—	—	—	1493.85
7 Kimi K3 Moonshot AISupported	Moonshot AI	Closed	Current	Reasoning	1.05M	$3.00 / $15.00	39	55.96s	74.87	72	68	79	89	72	—	—	—	1488.67
8 GPT-5.5 OpenAISupported	OpenAI	Closed	Superseded	Reasoning	1M	$5.00 / $30.00	84	64.16s	73.27	64	68	64	71	73	—	93	70	1482.09
9 Qwen3.8 Max AlibabaSupported Self-host	Alibaba	Open	Current	Reasoning	1M	Not listed	39	53.97s	72.43	68	61	87	86	69	—	91	—	1479.56
10 Claude Opus 4.8 AnthropicSupported	Anthropic	Closed	Superseded	Reasoning	1M	$5.00 / $25.00	62	40.77s	72.3	63	67	55	88	72	—	75	65	1472.85
11 Muse Spark 1.2 MetaEstimated	Meta	Closed	Superseded	Reasoning	1M	$1.25 / $4.25	154	28.37s	71.88	64	60	79	—	72	—	—	—	—
12 Muse Spark 1.1 MetaSupported	Meta	Closed	Superseded	Reasoning	1M	Not listed	217	12.12s	71.78	63	60	79	77	71	—	—	—	1492.06
13 GPT-5.6 Terra OpenAIEstimated	OpenAI	Closed	Current	Reasoning	1.05M	$2.50 / $15.00	Not measured	Not measured	71.44	61	67	63	76	70	—	87	97	—
14 GPT-5.4 OpenAISupported	OpenAI	Closed	Superseded	Reasoning	1.05M	$2.50 / $15.00	136	144.65s	70.96	56	54	57	69	69	—	90	65	1465.61
15 Claude Sonnet 5 AnthropicSupported	Anthropic	Closed	Current	Reasoning	1M	$2.00 / $10.00	82	176.88s	70.76	66	64	76	77	67	—	—	—	1462.37
16 Claude Opus 4.7 AnthropicSupported	Anthropic	Closed	Current	Standard	1M	$5.00 / $25.00	52	18.34s	70.22	59	63	—	—	65	—	—	61	1494.48
17 Gemini 3.7 Flash GoogleEstimated	Google	Closed	Superseded	Reasoning	1M	$0.75 / $3.75	320	10.89s	70.21	61	63	79	83	71	—	—	—	—
18 Grok 4.6 xAISupported	xAI	Closed	Current	Reasoning	500K	$2.00 / $6.00	65	49.70s	70.19	70	67	75	—	71	—	—	—	1461.15
19 Gemini 3.6 Flash GoogleSupported	Google	Closed	Superseded	Reasoning	1M	$1.50 / $7.50	209	15.68s	70.11	51	59	78	82	69	—	—	—	1483.14
20 Gemini 3.5 Flash GoogleSupported	Google	Closed	Superseded	Reasoning	1M	$1.50 / $9.00	205	15.26s	70.01	51	58	60	86	68	—	87	55	1479.43
21 Claude Opus 4.7 (Adaptive) AnthropicEstimated	Anthropic	Closed	Superseded	Reasoning	1M	$5.00 / $25.00	Not measured	Not measured	69.94	61	60	50	50	62	—	—	—	1502.21
22 Claude Opus 4.6 AnthropicSupported	Anthropic	Closed	Superseded	Standard	1M	$5.00 / $25.00	37	2.64s	69.84	54	56	66	59	62	—	52	59	1497.57
23 Gemini 3.1 Pro GoogleSupported	Google	Closed	Established	Reasoning	1M	$2.00 / $12.00	116	25.80s	69.82	40	46	51	79	65	—	—	54	1486.73
24 GPT-5.2 Pro OpenAISupported	OpenAI	Closed	Established	Reasoning	400K	$21.00 / $168.00	Not measured	Not measured	68.73	—	—	—	—	—	—	—	—	1440.15
25 Grok 4.5 xAISupported	xAI	Closed	Superseded	Reasoning	500K	$2.00 / $6.00	56	10.19s	68.64	63	63	44	78	70	—	—	—	1471.08

Showing 25 of 411

Reading the table

Use rank to shortlist, then inspect the evidence

The BenchLM LLM leaderboard 2026 ranks 232+ models and tracks 417+ large language models side by side across 422 benchmarks — from SWE-bench and LiveCodeBench for coding to GPQA Diamond and MMLU-Pro for knowledge and reasoning. Whether you need the best AI models 2026 has to offer for agentic workflows, math, multilingual tasks, or instruction following, our AI benchmark comparison tables make it easy to see how GPT-5, Claude, Gemini, DeepSeek, Llama, and dozens of other frontier and open-source models stack up on both benchmarks and operator tradeoffs like price and context. Supported and Estimated labels separate evidence strength from score, so incomplete reporting does not automatically remove a model from the comparison.

Embed the live leaderboard

Dataset journal

What changed in September 2026

Claude Fable 5.1 (Anthropic) holds the #1 spot on the BenchAlign leaderboard at 82.95.
8 model releases tracked in September 2026.
Google climbed 1 spot in the provider race.
130 Supported and 102 Estimated models appear in the public leaderboard.

Data verified September 4, 2026

Build a head-to-head comparison

Choose any two ranked models. The comparison opens with the decision, exact units, and evidence coverage.

versus

Compare these models

Six-month release record

The AI race, read as a record instead of a spectacle

Track which release led its month, how provider depth changed, and whether the crown moved.

Months: 6
Releases: 149
Lead changes: 5

Explore the release timeline

Best ranked model released in Sep 2026

Claude Fable 5.1Anthropic

Score82.95

RankProviderTop-three avg.Models

01Anthropic81.520

02OpenAI7839

03Google72.919

The evidence map

Explore benchmarks by category

Move from the overall ranking into the capability or workload that actually decides your model choice.

AgenticTools, browsers, and long-running work88 CodingRepository tasks and code generation62 MultimodalDocuments, images, and grounded work65 ReasoningLong-context and abstract reasoning29 KnowledgeProfessional and scientific knowledge50 Instruction followingConstraint and format reliability4 MultilingualCross-language accuracy and coverage13 MathContest and frontier mathematics32

Popular comparisons

Claude Fable 5.1 vs GPT-6 Astra GPT-6 Astra vs GPT-5.6 Sol Claude Fable 5.1 vs Claude Opus 5 GPT-6 Astra vs Claude Opus 5 Claude Fable 5.1 vs Claude Fable 5 Gemini 3.8 Flash vs GPT-6 Astra Gemini 3.8 Flash vs Gemini 3.7 Flash Grok 4.6 vs GPT-5.6 Sol GLM-5.3 vs Kimi K3

Tools and resources

AI Prompt WriterTurn the work you need into a testable prompt Prompt OptimizerGet closer to usable output with a clearer prompt LLM Pricing ComparisonCompare API costs across models Alternative FinderFind the best ChatGPT or Claude replacement Which LLM Should I Use?Get a personalized recommendation Cost CalculatorEstimate your monthly API spend Methodology & ExplainersHow BenchLM scores and curates benchmarks

Scoring methodology8 weighted categories, 37 ranking benchmarks, and 306 display-only records.Inspect method

Each model's overall score is a normalized weighted average of category averages. Within each category, benchmark results are normalized to a common scale and combined using weights that favor harder, less-saturated evaluations.

Confidence remains separate from score. It shows how much public benchmark evidence supports a result, while display-only benchmarks stay visible for context without receiving ranking weight.

Data comes from OpenBench, official model papers, and public leaderboards. External consensus signals are bounded calibration inputs and are not exposed in exported data.

Read the complete methodology

Category weights: 100%
Scored categories: 8
Ranking benchmarks: 37
Display-only: 306

Category and weightBenchmarks that affect the scoreCoverage

Agentic22%
Terminal-Bench 2.0 · BrowseComp · OSWorld-Verified · OSWorld 2.0 · AutomationBench
5 weighted · 83 context-only
Coding20%
SWE-bench Verified · SWE-Rebench · LiveCodeBench · SWE-bench Pro · SWE Multilingual · SciCode · LiveCodeBench (Vals)
7 weighted · 55 context-only
Reasoning17%
LongBench v2 · MRCRv2 · ARC-AGI-2 · ARC-AGI-3 · AA-LCR
5 weighted · 24 context-only
Multimodal12%
MMMU-Pro · AA-MMMU-Pro · OfficeQA Pro · CharXiv
4 weighted · 61 context-only
Knowledge12%
GPQA · SuperGPQA · MMLU-Pro · HLE · AA-Omniscience Accuracy · SimpleQA · HLE w/o tools · MMLU-Pro (Vals)
8 weighted · 42 context-only
Multilingual7%
MMLU-ProX
1 weighted · 12 context-only
Instruction Following5%
IFBench · AA-IFBench
2 weighted · 2 context-only
Math5%
AIME26 · HMMT Feb 2026 · FrontierMath v2 (Tiers 1-3) · FrontierMath v2 (Tier 4) · USAMO 2026
5 weighted · 27 context-only

Browse BenchLM

Tools & calculators

Tools

LLM Leaderboard & AI Model Benchmarks — September 2026