← Back to dashboard
OpenAI·LLM — weighted competency·Tue 25 Aug 2026

GPT-5.4

GPT-5.4 scores 82/100 competency for LLM at $5.63.

High confidence
Competency
82/100
category rank #22
Cost
$5.63/1M tok
blended
Speed
40/100
Slow
Accuracy
no data yet

Score history.

Weighted LLM competency · last 12 weeks · weekly snapshot.

82/100
+0 pts vs prior
77
16 Jun19 Jun23 Jun26 Jun29 Jun3 Jul6 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
71
Content Writing15% of category weight
75
Research & Analysis16% of category weight
79
Summarization12% of category weight
83
Translation7% of category weight
87
Reasoning16% of category weight
88
Knowledge14% of category weight
65

Pricing.

Published usage pricing. Figures refresh daily from our pricing sources.

$5.63

Usage pricing

$5.63/1M tok
Input
$2.50 / 1M tokens
Output
$15.00 / 1M tokens

Effort modes.

Same model, different reasoning effort — the competency/cost trade-off across modes.

ModeCompetencyCostSpeed
Default82 / 100$5.6340 / 100
Low62 / 100$5.6340 / 100

Where it sits.

Position against the rest of the category. Ranked by weighted competency.

RankModelScoreCostSpeedΔ vs GPT-5.4
01Grok 4.698$3.0027 / 100+16
02Claude Opus 597$10.0027 / 100+15
03GPT-5.6 Sol96$8.0031 / 100+14
04Claude Fable 595$20.0033 / 100+13
05Gemini 3.7 Flash94$1.5060 / 100+12
06Kimi K394$6.0018 / 100+11
07Qwen3.8 2.4T A95B92$3.0024 / 100+10
08Qwen3.8 Max89$3.0017 / 100+7
09GPT-5.589$11.2540 / 100+6
10GPT-5.6 Terra88$4.5057 / 100+6
11DeepSeek V4 Pro 081387$1.9849 / 100+5
12DeepSeek V4 Flash 073184$0.6678 / 100+1
13Claude Sonnet 583$4.0042 / 100+1
14Gemini 3.1 Pro Preview81$4.500 / 100-2
15GLM-5.280$2.1540 / 100-2