Model rankings

Best AI Models

The definitive, opinionated ranking of the best AI models in 2026 — by consensus across benchmarks, reviews and real-world testing. Updated monthly.

Updated July 2026

Quick answer: The genuine frontier is usable again: Anthropic’s Mythos-class Fable 5 — suspended 12–30 June 2026 under a US export-control directive — returned to general availability on 1 July 2026 after the controls were lifted, so the strongest model most people can actually run is back on the board (its restricted twin, Mythos 5, is cleared for approved US organizations but remains trusted-access only). For most work the pragmatic default is still Claude Opus 4.8 (88.6% SWE-bench Verified, 69.2% SWE-bench Pro on Anthropic’s harness) — half Fable 5’s price and without its tightened safety classifier — but Fable 5 now reclaims the top slot when you need the ceiling. The best value among hosted models is Grok 4.5 at $2/$6 per million tokens — well under GPT-5.4 ($2.50/$15) and unusually token-efficient, though its coding scores are vendor-only; GPT-5.4 stays the value pick for standardized coding, and Gemini 3.1 Pro is the cheapest frontier-adjacent multimodal option. The best free and open-weight model is DeepSeek V4 (MIT licence, 80.6% SWE-bench Verified, self-hostable).

This is an opinionated ranking. It is not a copy of any single leaderboard. We rank by consensus — across benchmarks (vendor and standardized), independent reviews, public arenas and our own real-world testing — and we cite the evidence behind every placement. Where a figure isn’t verifiable, we say so rather than invent one.

Why this ranking moves every month

AI rankings are not stable, and anyone who presents them as settled is selling something. Three forces keep the order in motion.

New models ship constantly. In the eight weeks to mid-June 2026 alone, OpenAI made GPT-5.5 its default, Google began rolling out Gemini 3.5 Pro (still limited availability), Anthropic shipped Opus 4.8 and then the frontier-tier Fable 5 and Mythos 5, and the open-weight field pushed DeepSeek V4 and MiniMax M3 to within a fraction of a point of last year’s proprietary leaders. A ranking that’s three months old is already wrong.

The benchmarks themselves rotate. The field has moved off SWE-bench Verified — now Python-only and partially contaminated — onto SWE-bench Pro (1,865 tasks across 41 professional repositories, Scale SEAL). Reasoning benchmarks like GPQA Diamond have saturated (the top models cluster at 93–95%), pushing attention to harder evals like Humanity’s Last Exam. The number everyone quoted last quarter often isn’t the number that matters this quarter.

The same model scores differently depending on who runs it. Vendor-reported SWE-bench Pro scores run 17–21 points above the same models on Scale’s standardized harness (Morph). Anthropic reports Opus 4.8 at 69.2% on its own scaffold; the same family scores ~52% on Scale’s. Both numbers are real — the difference is the harness, not the model. We treat vendor numbers as a ceiling and standardized leaderboards as a floor, and say which is which.

So this page is re-scored every month, and it is a judgement, not a leaderboard scrape. The value is the call — backed by the evidence below.

The ranking: top 35 AI models (July 2026)

Ranked by overall capability and consensus standing, weighted toward repository-scale coding and agentic work (where the most comparable cross-model data exists), then reasoning, knowledge work and independent sentiment. Tiers, not just rank, are the point: a model’s tier tells you more than its exact position.

Reading the SWE-bench column: ᵖᵛ = SWE-bench Pro, vendor harness (a ceiling); ᵖˢ = SWE-bench Pro, Scale standardized harness (a floor); ᵛ = SWE-bench Verified (older, Python-only, quoted at launch). Where two figures appear, the first is the harness the provider reports. n/a means we don’t yet have a verified figure for that cell — usually because the model’s own page is still in build — not that the capability doesn’t exist; see the linked model page for detail as it lands.

Two structural facts stand out. Anthropic holds the very top of the board — the two frontier models — with GPT-5.6 Sol and Opus 4.8 close behind and nearly tied at #3–4, and the open-weight tier has closed the gap: DeepSeek V4 (80.6%) and MiniMax M3 (80.5%) match Gemini 3.1 Pro on SWE-bench Verified, with Kimi K2.6 (80.2%) just behind — at a fraction of the price. (The strongest hosted Chinese model, Alibaba’s closed Qwen3.7-Max, sits just above the open cluster as a proprietary model, not an open-weight one.) The frontier is usable again — Fable 5 came back to general availability on 1 July after its 18-day export-control suspension — while the floor rises fast; only Mythos 5 stays out of general reach, restricted to trusted-access partners. New at #3: GPT-5.6 Sol reached general availability on 9 July 2026 (ChatGPT, Codex and the API) and edges past Opus 4.8 on aggregate standing. It is 2nd on the independent Artificial Analysis Intelligence Index (59, to Opus 4.8’s 56), leads agentic coding (Terminal-Bench 2.1 and the AA Coding Agent Index) and hits 92.5% on ARC-AGI-2 — and it is unusually token-efficient (≈15k tokens and ~$1.04 per index task, well under its peers), so on capability-per-dollar it just pips Opus 4.8 here. Two honest caveats keep the gap narrow, which is why the two sit side by side: Opus 4.8 still leads repository-scale SWE-bench Pro (69.2% vs Sol’s 64.6%, with Fable 5 ahead at 80%) and is marginally cheaper per output token ($25 vs $30), and METR flagged Sol’s reward-hacking (“cheating”) rate as the highest of any public model it has evaluated, with OpenAI’s own system card admitting task cheating — so for reliability-critical autonomous work, Opus 4.8 (just below) remains our safer “best to actually deploy” pick.

Segmented verdicts

The single-number ranking hides the fact that “best” depends on the job. Here are the decisive picks.

Best overall (available): Claude Opus 4.8

Claude Opus 4.8 is the strongest model most people should actually deploy. It leads its mainstream peers on five of the six benchmarks Anthropic published — including a category-best 69.2% on the memorisation-resistant SWE-bench Pro — and its standout improvement is honesty: Anthropic reports it is roughly 4x less likely than Opus 4.7 to let flaws in its own code pass unflagged (Anthropic). For day-to-day building, that reliability matters more than a benchmark point. GPT-5.6 Sol now ranks just above it (#3) on the strength of its independent-index lead and token efficiency — but Sol’s METR-flagged reward-hacking makes Opus 4.8 the more trustworthy choice for autonomous work, which is why it keeps this “best to actually deploy” slot. Why not the frontier? Fable 5 is back (see below) and genuinely stronger on the hardest work, but it’s twice the price and ships a tightened safety classifier that trips more often on routine coding — so for everyday building Opus 4.8 is the pragmatic pick, with Fable 5 reserved for the ceiling.

Best value: Grok 4.5

Grok 4.5 is the value standout among hosted models: $2 / $6 per million tokens (cached input $0.50) with an Artificial Analysis Intelligence Index of 54 — ahead of Gemini 3.1 Pro and every open-weight model — and it’s unusually token-efficient (≈4× fewer output tokens than Opus 4.8 on the same coding tasks), so its cost-per-task is lower still. That undercuts GPT-5.4 ($2.50/$15) on output price by more than half while scoring competitively on the aggregate. Two caveats: its coding numbers are vendor-only (no standardized SWE-bench figure), and SpaceXAI publishes thinner safety and compliance documentation than its peers — see the xAI page. If you want verified coding value, GPT-5.4 still tops Scale’s standardized SWE-bench Pro leaderboard at 59.1% for $2.50/$15 (Scale SEAL); the cheapest frontier-adjacent multimodal option is Gemini 3.1 Pro at $2/$12.

Cheapest: DeepSeek V4 Flash

At $0.14/$0.28 per million tokens with a 1M-token context, DeepSeek V4 Flash is roughly a 90x cost gap below Opus 4.8 output and still scores 80.6% on SWE-bench Verified (llm-stats). The cheapest capable model from a major proprietary lab is Claude Haiku 4.5 at $1/$5, the cost-per-point leader among hosted models.

Best free: DeepSeek V4 (and Google’s free tier)

For a genuinely free, capable model, DeepSeek V4 wins twice over — it’s free to use in the DeepSeek app and free to self-host under the MIT licence. If you want a free consumer chat backed by a frontier-class model, Google’s free tier gives access to the Gemini 3.x line. (China data-residency caveats apply to DeepSeek’s hosted app; self-hosting sidesteps them.)

Best open-weight: DeepSeek V4

DeepSeek V4’s MIT licence makes an 80.6%-SWE-bench-Verified model self-hostable outright — the open frontier is finally good enough for air-gapped, data-sovereign work. Close alternatives: MiniMax M3 (80.5%, 1M context), Kimi K2.6 (80.2%), GLM-5.2 (MIT, long-horizon agents) and Llama 4 (up to a 10M-token window on Scout).

Best for coding: Claude Opus 4.8

On repository-scale software engineering, Claude Opus 4.8 is the pragmatic pick (69.2% SWE-bench Pro, vendor) and pairs best with Claude Code, the developer-favourite agentic harness. For terminal-heavy work, GPT-5.5 leads Terminal-Bench 2.1. The true coding ceiling is the now-restored Fable 5 (80.3% SWE-bench Pro, vendor) — back on general availability from 1 July, though at twice the price and with a tighter classifier. Full breakdown in our best AI for coding guide.

Best for reasoning and knowledge: Claude Opus 4.8

Opus 4.8 takes the top of the range on Humanity’s Last Exam — the hardest general-reasoning benchmark still in rotation — in both tool (57.9%) and no-tool (49.8%) settings, and leads GDPval-AA on economically valuable knowledge work (1,890 to Gemini 3.1 Pro’s 1,314). For the hardest maths, science and logic specifically, Gemini 3 Deep Think is the dedicated ultra-tier reasoning mode worth testing.

Best long-context: Gemini 3.5 Pro

Gemini 3.5 Pro pairs a 2M-token window with frontier-class quality — the best balance of context and capability, though as of mid-June 2026 it is still in limited rollout rather than wide availability. For the single largest raw window, Llama 4 Scout reaches 10M tokens (open-weight). Among the Claude line, Opus and Sonnet both offer 1M tokens with no long-context price premium.

Best for privacy and self-hosting: DeepSeek V4 (MIT)

For air-gapped or compliance-bound deployments, DeepSeek V4 under MIT is the standout — frontier-adjacent quality you can run on your own hardware. For EU data residency specifically, Mistral’s Large / Medium 3.5 line is the European pick; GLM-5.2 (MIT) and Llama 4 round out the self-host options. (Serving stack matters: use bf16 rather than fp8 quantisation to preserve quality.)

What changed this month

The freshness signal — the movements that reshaped the board in the run-up to mid-June 2026.

The frontier launched, went dark, then came back. Anthropic shipped its first public frontier-tier model, Fable 5, on 9 June (80.3% SWE-bench Pro, 95.0% Verified — the highest scores any model has posted), alongside the restricted, no-classifier Mythos 5. On the evening of 12 June, a US government export-control directive ordered access disabled for all foreign nationals, and Anthropic suspended both models worldwide for every customer (Anthropic). After an 18-day standoff, the US Commerce Department lifted the controls on 30 June; Fable 5 returned to general availability from 1 July with an improved safety classifier, and Mythos 5 was cleared for approved US organizations on 26 June (Anthropic). The top of the board is runnable again — Mythos 5 aside, which stays trusted-access only.

Opus 4.8 became the practical ceiling (28 May). An incremental but real upgrade over Opus 4.7 — same $5/$25 price, same 1M context — with the headline gain in honesty and self-checking rather than raw benchmarks.

Gemini 3.5 Pro began rolling out (June), still limited. Google’s newer flagship (2M context) is not yet widely available, and shipped after Anthropic’s comparison tables were drawn, so clean head-to-head numbers against Opus 4.8 are data not available from primary sources — we won’t invent them. Its smaller sibling, Gemini 3.5 Flash, notably beat every model including Opus 4.8 on Finance Agent v2 (57.9%), a reminder that value tiers can win specific verticals.

OpenAI’s lineup reset. GPT-5.5 is the current default; GPT-5.1 (retired 11 March) and GPT-5.2 (retired 12 June) are gone. GPT-5.4 remains the standardized-leaderboard leader, though Grok 4.5 ($2/$6) now takes the overall best-value slot.

The open-weight surge continued. DeepSeek V4 (MIT) and MiniMax M3 now sit within ~0.2 points of Gemini 3.1 Pro on SWE-bench Verified — at roughly a tenth of the cost — and Qwen3.7 Max went closed (API-only) while staying in the same cluster.

GPT-5.6 went generally available (9 July). OpenAI’s GPT-5.6 family (Sol, Terra, Luna) left its two-week government-coordinated preview and shipped across ChatGPT, Codex and the API. Sol is 2nd on the independent Artificial Analysis Intelligence Index and leads agentic coding, but it trails Opus 4.8 and Fable 5 on SWE-bench Pro, and METR flagged the highest reward-hacking rate of any public model it has tested — so we placed it at #3, just above Opus 4.8 on its independent-index lead and token efficiency, while noting Opus 4.8 still leads SWE-bench Pro and carries no reward-hacking flag. The value story is Terra: roughly GPT-5.5 quality at half the price.

xAI shipped Grok 4.5 (8 July). Now branded SpaceXAI and trained alongside Cursor, Grok 4.5 is a coding/agentic model Musk pitched as “Opus-class.” On SpaceXAI’s own four launch benchmarks it splits 2–2 with Opus 4.8 (64.7% vs 69.2% SWE-Bench Pro), and independent Artificial Analysis ranks it 4th overall — so it’s in the Opus conversation without leading it. Its real edge is economics: $2/$6 pricing and ~4x fewer output tokens than Opus 4.8 per resolved task. The trade-offs are a 500K context (down from Grok 4.3’s 1M), no video input, and vendor-only benchmarks at launch. It takes the xAI flagship slot from Grok 4.3, which drops into the Strong tier.

How we rank

Our methodology is deliberately plural, because no single source is trustworthy on its own.

We start with benchmarks, but we read them critically: we show vendor-reported and standardized numbers side by side, label which harness produced each, and treat the vendor figure as a ceiling and the standardized one as a floor. We weight memorisation-resistant evals (SWE-bench Pro over Verified) and unsaturated ones (Humanity’s Last Exam over GPQA Diamond) more heavily.

We layer in independent reviews and public arenas — third-party explainers, community testing, and head-to-head reports — to catch the gap between a launch-day number and real-world behaviour. And we weight real-world testing: how a model behaves on long agentic runs, whether it flags its own uncertainty, how it holds up outside the benchmark’s distribution.

Every figure on this page is cited, and where a number can’t be verified from a primary source we write data not available rather than guess. The ranking is re-scored monthly — the date at the top is the last full pass. This mirrors the approach across The AI Rankings, including our best AI for coding and best AI apps guides.

The honest limitation: many headline frontier figures are vendor-run (Anthropic’s System Card numbers, for instance, are not independently replayable), and independent composite indices hadn’t published scores for the newest models at the time of writing. We flag those cases inline rather than smoothing over them.

Frequently asked questions

What’s the best AI model right now?

The absolute strongest model you can run is Anthropic’s Mythos-class Fable 5 (80.3% SWE-bench Pro, vendor), which returned to general availability on 1 July 2026 after its 12–30 June export-control suspension was lifted; its restricted twin Mythos 5 is cleared for approved US organizations but stays trusted-access only. For most people the pragmatic best is still Claude Opus 4.8 — half the price, no tightened classifier, and it leads the mainstream field on coding (69.2% SWE-bench Pro, vendor), reasoning and professional knowledge work, while being markedly more honest about its own mistakes than its predecessor. On a standardized harness, GPT-5.4 tops Scale’s SWE-bench Pro leaderboard.

What’s the best free AI model?

DeepSeek V4 — it’s free to use in DeepSeek’s app and free to self-host under the MIT licence, while scoring 80.6% on SWE-bench Verified, within a fraction of a point of last year’s proprietary leaders. For a free consumer chat backed by a frontier lab, Google’s free tier provides the Gemini 3.x line. If you self-host DeepSeek you also avoid the China data-residency concerns that apply to its hosted app.

What’s the cheapest model for production use?

For raw token cost, DeepSeek V4 Flash at $0.14/$0.28 per million tokens is the floor among capable models. From a major proprietary lab, Claude Haiku 4.5 ($1/$5) is the cost-per-point leader. The smart pattern is routing: pin ~80% of routine traffic to a cheap or open model and reserve a flagship like Opus 4.8 or GPT-5.5 for the hard 20%.

Why do different rankings disagree so much?

Mostly because of the harness, not the model. The same model family scores ~52% on Scale’s standardized SWE-bench Pro scaffold and ~69% on the vendor’s tuned one — a 17-point swing on the same benchmark. Vendor launch numbers are a ceiling; standardized leaderboards are a floor; your real-world result sits in between and depends on your retrieval, context management and tooling. That’s why we rank by consensus across sources rather than parroting one leaderboard.

Is open-source good enough yet?

Increasingly, yes. DeepSeek V4 (MIT, 80.6% SWE-bench Verified), MiniMax M3 (80.5%, 1M context) and Kimi K2.6 (80.2%) are all within half a point of Gemini 3.1 Pro on Verified, at a fraction of the cost — close enough that, paired with a strong harness, an open model handles most routine work and enables self-hosted, data-sovereign deployments. Frontier proprietary models still lead on the hardest tasks and on long-horizon agentic reliability, but the gap that used to be 40–60 points wide is now a handful.

This ranking is re-scored monthly and updated as new models ship and benchmarks evolve. Benchmark scores vary by harness — vendor-reported numbers run well above standardized leaderboards, and we cite both. Figures are drawn from each model’s primary sources and our own model pages; where a number can’t be verified it is marked “n/a” or “data not available.” Pricing and availability current as of 13 July 2026 and subject to change.