AI ranking
Cost / performance
The ratio between overall performance and the public monthly subscription (Claude.ai Pro, ChatGPT Plus, Gemini Advanced…). API prices and per-token costs are not taken into account.
Top visuel
- 01 Exaone 4.5 33b (non Reasoning) 100.00
- 02 Gemini 3 deep think 99.99
- 03 GPT 3.5 turbo (0613) 99.98
- 04 GPT 4o mini realtime (dec '24) 99.97
- 05 GPT 4o realtime (dec '24) 99.96
- 06 GPT 5.5 pro (xhigh) 99.95
- 07 Mi:dm k 2.5 pro preview 99.94
- 08 Deepseek chat v3 (prev) 99.93
- 09 Grok 3 mini beta (high) 99.78
- 10 Grok 3 mini beta (low) 99.75
Compare models. Cochez jusqu'à 3 modèles dans le tableau ci-dessous, puis lancez la comparaison : qui gagne sur quel usage, de combien, et avec quelle solidité.
| # | Model | Vendor | Score | Monthly subscription | Assessment | |
|---|---|---|---|---|---|---|
| 01 | Lg ai research | 100.00 / 100 | Non disponible | Partial | ||
| 02 | 99.99 / 100 | 22 €/mois | Partial | |||
| 03 | OpenAI | 99.98 / 100 | 23 €/mois | Partial | ||
| 04 | OpenAI | 99.97 / 100 | 23 €/mois | Partial | ||
| 05 | OpenAI | 99.96 / 100 | Prix API | Partial | ||
| 06 | OpenAI | 99.95 / 100 | 23 €/mois | Partial | ||
| 07 | Mi:dm k 2.5 pro preview | Korea telecom | 99.94 / 100 | Non disponible | Partial | |
| 08 | DeepSeek | 99.93 / 100 | Gratuit | Partial | ||
| 09 | xAI | 99.78 / 100 | Gratuit | Partial | ||
| 10 | xAI | 99.75 / 100 | Gratuit | Partial | ||
| 11 | Cogito v2.1 (reasoning) | Deep cogito | 99.67 / 100 | Non disponible | Partial | |
| 12 | 99.56 / 100 | 22 €/mois | Partial | |||
| 13 | DeepSeek | 99.47 / 100 | Gratuit | Partial | ||
| 14 | 99.18 / 100 | 22 €/mois | Partial | |||
| 15 | Mistral | 99.11 / 100 | 15 €/mois | Partial | ||
| 16 | OpenAI | 96.56 / 100 | 23 €/mois | Partial | ||
| 17 | Anthropic | 96.50 / 100 | 23 €/mois | Partial | ||
| 18 | Anthropic | 96.49 / 100 | 23 €/mois | Partial | ||
| 19 | Anthropic | 96.33 / 100 | 23 €/mois | Partial | ||
| 20 | Anthropic | 95.98 / 100 | 23 €/mois | Partial | ||
| 21 | Anthropic | 95.80 / 100 | 23 €/mois | Partial | ||
| 22 | 95.57 / 100 | 22 €/mois | Partial | |||
| 23 | OpenAI | 95.41 / 100 | 23 €/mois | Partial | ||
| 24 | Anthropic | 95.10 / 100 | 23 €/mois | Partial | ||
| 25 | Anthropic | 94.58 / 100 | 23 €/mois | Partial | ||
| 26 | xAI | 94.25 / 100 | Gratuit | Partial | ||
| 27 | Meta | 94.23 / 100 | Non disponible | Partial | ||
| 28 | Anthropic | 94.06 / 100 | 23 €/mois | Partial | ||
| 29 | Anthropic | 93.71 / 100 | 23 €/mois | Partial | ||
| 30 | Anthropic | 93.03 / 100 | Gratuit | Partial | ||
| 31 | 93.01 / 100 | 22 €/mois | Partial | |||
| 32 | OpenAI | 92.45 / 100 | 23 €/mois | Partial | ||
| 33 | Anthropic | 92.31 / 100 | 23 €/mois | Partial | ||
| 34 | Anthropic | 91.68 / 100 | 23 €/mois | Partial | ||
| 35 | OpenAI | 91.43 / 100 | 23 €/mois | Partial | ||
| 36 | Anthropic | 91.26 / 100 | 23 €/mois | Partial | ||
| 37 | OpenAI | 91.25 / 100 | 23 €/mois | Partial | ||
| 38 | xAI | 91.24 / 100 | Gratuit | Partial | ||
| 39 | Alibaba | 91.23 / 100 | Non disponible | Partial | ||
| 40 | Anthropic | 91.08 / 100 | 23 €/mois | Partial | ||
| 41 | 90.91 / 100 | 22 €/mois | Partial | |||
| 42 | OpenAI | 90.90 / 100 | 23 €/mois | Partial | ||
| 43 | OpenAI | 90.75 / 100 | 23 €/mois | Partial | ||
| 44 | Anthropic | 90.73 / 100 | 23 €/mois | Partial | ||
| 45 | xAI | 90.72 / 100 | Gratuit | Partial | ||
| 46 | Anthropic | 90.66 / 100 | 23 €/mois | Partial | ||
| 47 | xAI | 90.56 / 100 | Gratuit | Partial | ||
| 48 | Anthropic | 90.38 / 100 | 23 €/mois | Partial | ||
| 49 | OpenAI | 90.20 / 100 | 23 €/mois | Partial | ||
| 50 | Baidu | 90.03 / 100 | Non disponible | Partial |
Score indicatif, pondéré à partir de sources publiques. Méthodologie transparente. Voir la page Classement IA pour la méthodologie complète et les autres catégories.
AI cost / performance ranking
Le Recul's Cost / performance ranking sets what a model is worth against what it actually costs in use. It draws on overall performance, price, speed, latency, stability and usable context — not on the headline price in isolation.
This is the most useful category when budget is a real constraint. Price gaps between models are far wider than quality gaps: on many everyday uses, a model two to ten times cheaper does an equivalent job. Paying for the top-ranked model only makes sense if your use genuinely requires what sets it apart.
The ranking does not tell you what to buy. It shows where the tipping point sits between what you pay and what you get, so the trade-off is made on figures rather than on an impression.
What this ranking is for
This ranking helps you avoid over-specifying: picking the most expensive model « just in case » is the most costly reflex and rarely the most justified.
It also helps spot the opposite case, where a cheap model ends up costing more in rework, latency or instability than a better-placed one.
Comment lire le classement
- Overall quality, weighted as in the general ranking.
- Effective price in use, input and output.
- Speed and latency, which govern interactive use.
- Stability: consistency of the service and of the answers.
- Usable context that can actually be exploited, not the theoretical limit announced.
FAQ — Cost / performance
Which AI offers the best value for money?
It depends on volume and use. The ranking sets performance against cost so that the trade-off is explicit, rather than imposing a single choice.
Does this ranking use subscriptions or API prices?
This category reasons on the effective cost in use. For consumer assistants billed as a monthly subscription, the Chat ranking is the reference.
Is a cheaper model necessarily worse?
No, and that is the whole point of this category. On many everyday uses, the quality gap is far smaller than the price gap.
Why does usable context differ from the announced context?
Because answer quality often degrades before the technical limit. The context you can genuinely exploit is usually smaller than the advertised window.
How often is the ranking updated?
About every 25 hours, automatically. The update date appears at the top of the page.