OpenAI·LLM — weighted competency·Tue 25 Aug 2026
OGPT-5.2 Codex
GPT-5.2 Codex scores 67/100 competency for LLM at $4.81.
High confidence
Competency
67/100
category rank #44
Cost
$4.81/1M tok
blended
Speed
40/100
Slow
Accuracy
—
no data yet
Score history.
Weighted LLM competency · last 12 weeks · weekly snapshot.
67/100
+0 pts vs prior
16 Jun19 Jun23 Jun26 Jun29 Jun3 Jul6 Jul10 Jul13 Jul17 Jul20 Jul23 Jul26 Jul30 Jul2 Aug5 Aug9 Aug12 Aug16 Aug19 Aug22 Aug25 Aug
What it's actually good at.
Score on each business-task subset that goes into the weighted competency.
Customer Service20% of category weight
56
Content Writing15% of category weight
60
Research & Analysis16% of category weight
64
Summarization12% of category weight
68
Translation7% of category weight
72
Reasoning16% of category weight
81
Knowledge14% of category weight
52
Pricing.
Published usage pricing. Figures refresh daily from our pricing sources.
$4.81
Usage pricing
$4.81/1M tok
- Input
- $1.75 / 1M tokens
- Output
- $14.00 / 1M tokens
Where it sits.
Position against the rest of the category. Ranked by weighted competency.
| Rank | Model | Score | Cost | Speed | Δ vs GPT-5.2 |
|---|---|---|---|---|---|
| 01 | SGrok 4.6 | 98 | $3.00 | 27 / 100 | +31 |
| 02 | AClaude Opus 5 | 97 | $10.00 | 27 / 100 | +30 |
| 03 | OGPT-5.6 Sol | 96 | $8.00 | 31 / 100 | +29 |
| 04 | AClaude Fable 5 | 95 | $20.00 | 33 / 100 | +28 |
| 05 | GGemini 3.7 Flash | 94 | $1.50 | 60 / 100 | +27 |
| 06 | KKimi K3 | 94 | $6.00 | 18 / 100 | +27 |
| 07 | AQwen3.8 2.4T A95B | 92 | $3.00 | 24 / 100 | +25 |
| 08 | AQwen3.8 Max | 89 | $3.00 | 17 / 100 | +22 |
| 09 | OGPT-5.5 | 89 | $11.25 | 40 / 100 | +22 |
| 10 | OGPT-5.6 Terra | 88 | $4.50 | 57 / 100 | +21 |
| 11 | DDeepSeek V4 Pro 0813 | 87 | $1.98 | 49 / 100 | +20 |
| 12 | DDeepSeek V4 Flash 0731 | 84 | $0.66 | 78 / 100 | +17 |
| 13 | AClaude Sonnet 5 | 83 | $4.00 | 42 / 100 | +16 |
| 14 | GGemini 3.1 Pro Preview | 81 | $4.50 | 0 / 100 | +13 |
| 15 | ZGLM-5.2 | 80 | $2.15 | 40 / 100 | +13 |