Capital & Compute
Leaderboard· Updated August 7, 2026

The AI model value leaderboard

Most rankings tell you which model scores highest. This one also tells you which model is worth the money. Each LLM is rated two ways: its independent benchmark score, and its value, the points it buys you per dollar of tokens. The two orders are not the same.

Which AI model is the best value right now?

On benchmark scores alone, the strongest LLM you can buy here is GPT-5.6 Sol (80.0 of 100 on the coding composite). But cost flips the ranking: GPT-5.6 Luna delivers about 166.7 coding points per dollar of blended token price, roughly 23.5x the value of GPT-5.6 Sol. The cheaper models, mostly from Chinese labs, win on value; the priciest US flagships win on raw capability. Which one is "best" depends entirely on whether you are buying ability or buying ability per dollar.

GPT-5.6 Luna
Best value, coding
166.7 coding points per dollar (blended)
GPT-5.6 Sol
Top coding score (buyable)
80.0 of 100 on the coding composite
$0.20
Cheapest to run
DeepSeek V4 Flash, blended (3:1) price per Mtok
29
Models tracked
16 scored on coding, 29 on intelligence

The value ladder, in one chart

Coding points per dollar of blended token price, for the models you can buy today. The ranking is almost the inverse of the raw-score ranking: the cheapest capable models sit at the top because they score within range of the frontier at a fraction of the price.

AI model coding value: composite coding score per dollar of blended token priceA lollipop chart ranking buyable models by coding value, defined as coding composite score divided by blended token price. The cheaper open-weight models rank highest; the most expensive flagship ranks lowest.0.050.0100.0150.0200.0GPT-5.6 Luna166.7MiniMax M3111.6Qwen3.7 Plus99.8Nemotron 3 Ultra36.5Kimi K2.7 Code35.5Devstral 234.8GLM-5.232.0Llama 4 Maverick31.8Grok 4.525.3Grok 4.322.5Qwen3.7 Max17.6GPT-5.6 Terra17.1Gemini 3.1 Pro15.3Claude Opus 4.87.4GPT-5.6 Sol7.1Claude Fable 53.8
AI model coding value: composite coding score per dollar of blended token price
ItemValue
GPT-5.6 Luna166.7
MiniMax M3111.6
Qwen3.7 Plus99.8
Nemotron 3 Ultra36.5
Kimi K2.7 Code35.5
Devstral 234.8
GLM-5.232.0
Llama 4 Maverick31.8
Grok 4.525.3
Grok 4.322.5
Qwen3.7 Max17.6
GPT-5.6 Terra17.1
Gemini 3.1 Pro15.3
Claude Opus 4.87.4
GPT-5.6 Sol7.1
Claude Fable 53.8
Coding value (composite score divided by blended token price) for buyable models. Higher is more coding ability per dollar. Blended price weights input to output 3 to 1.Source: Price Per Token (composite scores) and Capital & Compute verified pricing

The same picture, on general intelligence

Coding has no score for every model, but the broader intelligence composite does, so this ladder includes all the buyable models, DeepSeek, the GPT-5 and GPT-5.6 tiers, Grok, Sonnet and Haiku among them. The story holds: the cheap models lead on value, and the priciest flagships (GPT-5.2 Pro, Claude Fable 5, Claude Opus 4.8) fall to the bottom, where a top score cannot outrun a high token price.

AI model intelligence value: composite intelligence score per dollar of blended token priceA lollipop chart ranking every buyable model by intelligence value, defined as intelligence composite score divided by blended token price. Cheap models such as DeepSeek V4 Flash, MiniMax M3 and Qwen3.7 Plus rank highest; expensive flagships such as GPT-5.2 Pro rank lowest.0.0100.0200.0300.0DeepSeek V4 Flash297.1GPT-5.6 Luna115.6MiniMax M384.6DeepSeek V4 Pro82.8Qwen3.7 Plus69.6Nemotron 3 Ultra28.0Llama 4 Maverick27.9Kimi K2.7 Code24.5GLM-5.223.8Devstral 221.3Qwen3.8 Max19.3Grok 4.518.7Inkling16.3Grok 4.315.9GPT-5.6 Terra12.7Qwen3.7 Max12.3Claude Haiku 4.511.9Gemini 3.1 Pro10.3Gemini 3.5 Flash10.3Kimi K310.0GPT-5.3 Codex9.2Gemini 3 Pro Preview7.4Claude Sonnet 4.65.7Claude Opus 4.85.6Grok 45.6GPT-5.6 Sol5.4GPT-5.25.4Claude Fable 53.0GPT-5.2 Pro0.7
AI model intelligence value: composite intelligence score per dollar of blended token price
ItemValue
DeepSeek V4 Flash297.1
GPT-5.6 Luna115.6
MiniMax M384.6
DeepSeek V4 Pro82.8
Qwen3.7 Plus69.6
Nemotron 3 Ultra28.0
Llama 4 Maverick27.9
Kimi K2.7 Code24.5
GLM-5.223.8
Devstral 221.3
Qwen3.8 Max19.3
Grok 4.518.7
Inkling16.3
Grok 4.315.9
GPT-5.6 Terra12.7
Qwen3.7 Max12.3
Claude Haiku 4.511.9
Gemini 3.1 Pro10.3
Gemini 3.5 Flash10.3
Kimi K310.0
GPT-5.3 Codex9.2
Gemini 3 Pro Preview7.4
Claude Sonnet 4.65.7
Claude Opus 4.85.6
Grok 45.6
GPT-5.6 Sol5.4
GPT-5.25.4
Claude Fable 53.0
GPT-5.2 Pro0.7
Intelligence value (composite score divided by blended token price) for every buyable model. Higher is more measured reasoning per dollar. The expensive flagships rank low here despite strong raw scores.Source: Price Per Token (composite scores) and Capital & Compute / source-dataset pricing

Rank it yourself

Switch the benchmark between coding and general intelligence, and switch the sort between value and raw score. The default view is coding, ranked by value.

Best LLM by coding, ranked by value

Composite of code generation, understanding, and problem-solving (0-100). Value is coding points per dollar of blended token price.

Live ranking
Benchmark

Coding: code-writing and problem-solving. Intelligence: general reasoning. Both are 0-100 composite scores.

Sort by

Value: points per dollar (best bang for the buck). Raw score: highest benchmark, price aside.

What is value? It is how many coding points you get per dollar of tokens: coding score ÷ blended price, where blended price = (3 × input + output) ÷ 4 per million tokens (input is weighted higher because coding agents read far more than they write). A higher value means more measured ability per dollar; it is a cost-efficiency measure, not a verdict on which model is best.
#ModelCodingInput $/MtokOutput $/MtokValue (pts/$)
1GPT-5.6 Luna OpenAI75.0$0.20$1.20166.7 Best value
2MiniMax M3 MiniMax58.6$0.30$1.20111.6
3Qwen3.7 Plus Alibaba55.9$0.32$1.2899.8
4Nemotron 3 Ultra Nvidia49.3$0.60$3.6036.5
5Kimi K2.7 Code Moonshot60.8$0.95$435.5
6Devstral 2 Mistral31.3$0.90$0.9034.8
7GLM-5.2 Zhipu68.8$1.40$4.4032.0
8Llama 4 Maverick Meta16.3$0.35$131.8
9Grok 4.5 xAI76.0$2$625.3
10Grok 4.3 xAI35.2$1.25$2.5022.5
11Qwen3.7 Max Alibaba66.0$2.50$7.5017.6
12GPT-5.6 Terra OpenAI77.0$2$1217.1
13Gemini 3.1 Pro Google68.8$2$1215.3
14Claude Opus 4.8 Anthropic74.3$5$257.4
15GPT-5.6 Sol OpenAI80.0$5$307.1
16Claude Fable 5 Anthropic76.5$10$503.8

Switch the benchmark or sort to re-rank. Scores are 0-100 composites from the source dataset. A ✓ next to the provider marks a price reconciled with our verified registry against the provider source; the rest are the author-direct or endpoint rate reported by the source dataset, not yet independently re-verified.

How to read this leaderboard

Two grounded inputs, one derived number. The benchmark scores are composite Coding and Intelligence scores read from the Price Per Token dataset, which aggregates independent benchmarks and cites Artificial Analysis, the HuggingFace Open LLM Leaderboard, and LayerLens. They are composites on a 0-100 scale, not a single named test. A few of the newest frontier models (the GPT-5.6 tiers and Grok 4.5) are not yet in that dataset, so their scores are read directly from Artificial Analysis and marked per row. The prices carry a check when they are reconciled with this site's own verified registry, the same numbers behind the model release tracker; the rest are the author-direct or endpoint rate reported by the source dataset, labeled per row and not yet independently re-verified. Each links to its provider source.

From those two, the leaderboard computes value: the benchmark score divided by a blended token price, where blended price weights input and output tokens 3 to 1, ((3 × input) + output) ÷ 4. The 3:1 mix mirrors how an agentic coding session actually bills: it reads far more context than it writes. Value is a cost-efficiency measure, not a verdict on quality. A model can top the value ranking and still be the wrong choice for work that needs the highest absolute score. It is the same lesson as the price reversal in per-task cost: the headline number and the number that matters are rarely the same.

The independence rule

This leaderboard sells no placement. Ranking is never for sale, and no model is promoted for payment. The entire point of a value table is to be a neutral referee of what each model actually costs to use; the day a vendor could pay to look cheaper, it would be worthless. The benchmark scores come from an independent third party; the prices come from primary provider sources.

What is not here, and why

A model is listed only once an independent composite score exists for it, so the table is not padded with vendor-reported numbers. That leaves a few notable models tracked but not yet ranked:

  • Claude Opus 5. Anthropic's new flagship, released July 24, 2026 at $5/$25 per Mtok (the same rate as Opus 4.8, which it replaces). Artificial Analysis rates it Intelligence Index 63 at max effort, re-read 2026-08-07 (up from 61), still the highest score on the index and just ahead of Fable 5 at 62 in its fallback configuration. It is also the most expensive model to evaluate: $3,836.05 to run the full Intelligence Index. Price Per Token, the base source this board uses, has not yet published a coding/intelligence composite for it. It is left off pending that composite to keep the Anthropic rows on one source; Opus 4.8 represents the tier below for now.
  • Claude Sonnet 5. Released June 30, 2026. Price Per Token has not yet published an independent coding/intelligence composite for it. Artificial Analysis scores it at Intelligence Index 55 at max effort, re-read 2026-08-07 (up from 53), and Anthropic's own launch benchmarks (SWE-bench Pro 63.2%, Terminal-Bench 2.1 80.4%) are self-reported; it is left off pending a Price Per Token composite to keep the Anthropic rows on one source.
  • GPT-5.5. OpenAI's prior flagship, now superseded by the GPT-5.6 family (Sol, Terra, Luna), which is scored above. Price Per Token has not published a composite for GPT-5.5 and it is no longer OpenAI's current tier, so it is not scored here.
  • Meta Muse Spark 1.1. Meta's first paid model, released July 9, 2026 at $1.25/$4.25 per Mtok. Artificial Analysis scores it at Intelligence Index 53 in the Xhigh Effort configuration, read 2026-08-07. That is 10 points above the 43 this note previously carried, which is far larger than the index-wide drift of the same period; the earlier read was recorded without a variant label, so it was most likely a lower-effort configuration rather than a change in the model. Treat the 43 as unattributable and the 53 as the Xhigh figure specifically. Artificial Analysis has since added a Meta Muse Spark 1.2 at 57 in the same configuration, which this board does not yet track. Price Per Token, the base source this board uses, has not published a composite for either. Muse Spark leads on tool-use and agentic tests but trails the frontier on coding. Meta Llama 4 Maverick represents Meta on the board for now.
  • Cohere North Mini Code. Free on hosted endpoints and open-weight, so a per-token value score is undefined. It posts a 33.4 Artificial Analysis Coding Index, which was not re-read on 2026-08-07 because the Coding Index is not exposed on the public models leaderboard; its Intelligence Index reads 20 there, a reminder that the two indices are different scales and must not be swapped for one another. The real cost is self-hosted compute, not a token rate.
  • Smaller and older variants. Models below roughly 10B parameters, superseded 2024-era releases (Claude 3.5, GPT-4 Turbo, o1), and narrowly tracked or unpriced entries are left off to keep the board to current, recognizable, buyable models.

For per-token rates and release dates across every model the site follows, see the AI model release tracker. To turn these rates into the cost of a real job, use the cost-per-task calculator or put two models head to head. To pay nothing at all, see which AI models are free to use and good enough to ship with.

Frequently asked questions

What is the best LLM for coding in 2026?
Among models you can actually buy, GPT-5.6 Sol posts the highest coding composite in this dataset, 80.0 of 100, just ahead of Claude Opus 4.8 and the restored Claude Fable 5. On a value basis, points bought per dollar, cheaper models such as GPT-5.6 Luna lead instead, because they score within range of the frontier at a fraction of the token price.
What is the best value AI model?
On the coding composite, GPT-5.6 Luna is the value leader at about 166.7 points per dollar of blended price, roughly 23.5 times GPT-5.6 Sol. Other low-cost models (Qwen3.7 Plus, Kimi K2.7) cluster near the top too, and on the intelligence composite DeepSeek V4 Flash leads outright at $0.14/$0.28 per Mtok. Value rewards low price, so it favors capable cheap models over the most expensive flagships: GPT-5.2 Pro, at $21/$168 per Mtok, lands last on value despite a top-tier score.
How is the value score calculated?
Value equals the benchmark composite score divided by a blended token price. The blended price weights input and output tokens 3 to 1: (3 times input + output) divided by 4, in dollars per million tokens. The 3:1 mix reflects agentic coding, which reads far more context than it writes. A higher value means more measured ability per dollar; it is a cost-efficiency measure, not a quality ranking on its own.
Where do the benchmark scores come from?
The composite Coding and Intelligence scores are read from the Price Per Token dataset, which aggregates independent benchmarks and cites Artificial Analysis, the HuggingFace Open LLM Leaderboard, and LayerLens. They are composite scores on a 0-100 scale, not a single named test. Scores for the newest frontier models the source dataset has not composited yet (the GPT-5.6 tiers and Grok 4.5) are read directly from Artificial Analysis, the same independent benchmark family it aggregates, and flagged per row. Prices marked with a check are reconciled with this site's own verified registry against the provider source; the rest are the author-direct or endpoint rate reported by the source dataset, labeled per row and not yet independently re-verified. This leaderboard sells no placement: ranking is never for sale.
Are Grok 4.5 and GPT-5.6 on the leaderboard?
Yes. GPT-5.6 (Sol, Terra, Luna) went generally available July 9, 2026 and Grok 4.5 released July 8, and both are scored here now. Because the Price Per Token dataset this board uses as its base has not published composites for them yet, their scores are read directly from Artificial Analysis (the same independent benchmark family Price Per Token aggregates) and flagged per row. GPT-5.6 Sol posts the top coding composite in the set; GPT-5.6 Luna is the best-value US model on coding; Grok 4.5 lands mid-pack on value at $2/$6 per Mtok.

Sources

  • Price Per Token. LLM API Pricing and Benchmarks dataset (composite Coding and Intelligence scores). Scores read 2026-07-13. https://pricepertoken.com/
  • Artificial Analysis. Independent LLM benchmarks and intelligence index (cited by the source dataset as a benchmark origin). https://artificialanalysis.ai/
  • Capital & Compute. AI model registry (verified per-token API prices, each linked to a provider source). /ai-models/

Machine-readable data: /ai-model-leaderboard.json.

← Back to Capital & Compute