← Back to dashboard
OpenAI·LLM — weighted competency·Wed 26 Aug 2026

GPT-5.4 mini

GPT-5.4 mini scores 62/100 competency for LLM at $1.69.

High confidence
Competency
62/100
weighted score
Cost
$1.69/1M tok
blended
Speed
0/100
throughput
Accuracy
5.5% halluc.
hallucination rate

Score history.

Weighted LLM competency · last 12 weeks · weekly snapshot.

62/100
— flat
0
16 Jun19 Jun23 Jun26 Jun27 Jun28 Jun29 Jun30 Jun1 Jul2 Jul3 Jul4 Jul5 Jul6 Jul7 Jul8 Jul9 Jul10 Jul11 Jul12 Jul13 Jul14 Jul15 Jul16 Jul17 Jul18 Jul19 Jul20 Jul21 Jul22 Jul23 Jul24 Jul25 Jul26 Jul27 Jul28 Jul29 Jul30 Jul31 Jul1 Aug2 Aug3 Aug4 Aug5 Aug6 Aug7 Aug8 Aug9 Aug10 Aug11 Aug12 Aug13 Aug14 Aug15 Aug16 Aug17 Aug18 Aug19 Aug20 Aug21 Aug22 Aug23 Aug24 Aug25 Aug26 Aug

What it's actually good at.

Score on each business-task subset that goes into the weighted competency.

Customer Service20% of category weight
52
Content Writing15% of category weight
55
Research & Analysis16% of category weight
59
Summarization12% of category weight
63
Translation7% of category weight
66
Reasoning16% of category weight
77
Knowledge14% of category weight
49

Pricing.

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

$1.69

Usage pricing

$1.69/1M tok
Input
$0.75 / 1M tokens
Output
$4.50 / 1M tokens

Where it sits.

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

RankModelScoreCostSpeedΔ vs GPT-5.4
24Solar Pro 466$0.5340 / 100+4
25Kimi K2 Thinking66$1.0840 / 100+4
26Hy365$0.2442 / 100+3
27MiMo-V2.5-Pro63$0.5422 / 100+2
28DeepSeek V3.263$0.320 / 100+1
29Grok 4.20 0309 v262$1.5640 / 100+0
30Qwen3.6 Plus62$1.1340 / 100+0
31GPT-5.4 mini62$1.690 / 100
32Inkling61$1.7623 / 100-1
33MiMo-V2.560$0.1829 / 100-2
34KAT Coder Pro V258$0.5372 / 100-4
35Grok 4.357$1.5640 / 100-4
36Qwen3.6 27B57$1.3540 / 100-5
37GLM-5-Turbo5540 / 100-6
38GPT-5.4 nano55$0.460 / 100-7