CADLE CAP
92
Cadle #29/385 · 83% confidence
OpenAI · ProprietaryOpenAI: GPT-5.4
Active
Model portfolio
OpenAI: GPT-5.4
Tap a star to rate
OpenAI · Released 2026-03-05 · v2026-03-05 · Closed · Context 1.1M tokens
OpenAI: GPT-5.4 is a closed model from OpenAI (released 2026-03-05). Context window ~1.1M tokens with capabilities: Vision, Text, Code, Reasoning. List pricing ≈ $2.50 / $15.00 per 1M input/output tokens. Top tracked signals: AGENTIC · benchlm 98.9, MATH · epoch 97.8, GPQA · epoch 94.9. Cadle merges provider listings, unified leaderboard medians, and public pricing where available.
Language Cap
92
Cadle Language #29/385 · 83%
Benchmark average
85.9
#27 on the benchmark matrix
Pricing
$2.50
$15.00 / 1M out · 5.1 pts/$
CROSS-BOARD RANKS
Cadle Language LLM #29/385Matrix #27/443BenchLM #31/224AA #75/698vs BenchLM: -3
CADLE CAP vs MODEL MATRIX
Cadle Cap ranks models on every published score we have for them — harder benchmarks weigh more. Missing tests are skipped, not zeroed. It answers who is stronger than whom in today's pool.
Model Matrix is the datasheet: Overall, Intelligence, Coding, Agentic, MMLU, GPQA, Math, LiveCodeBench, HumanEval, Reason, ARC-AGI. A dash means unmeasured. AVG is an importance-weighted mean of that model's filled cells only.
MODEL MATRIX · TRUTH CENTER CELLS
Overall
66.6
AA IQ
39.0
Coding
76.9
Agentic
93.0
MMLU
91.7
GPQA
92.8
Math
89.9
LiveCodeBench
87.5
HumanEval
—
Reason
83.8
ARC-AGI
74.0
Coverage AVG
85.9
Cadle Cap ranks models with within-benchmark percentiles so ARC-AGI ~40 and MMLU ~90 never compete raw. Coverage AVG is an importance-weighted mean of filled expert cells only — blanks are skipped, not zeroed.
ANALYSIS · TRUTH CENTER
Hard benches (GPQA · ARC-AGI · LCB · Agentic) sit left — a mid-40 on ARC-AGI can still be frontier. Broader benches on the right are easier and often higher.
CADLE INSIGHTS
Only measured signals
INTELLIGENCE
48.8
Media Cap quality axis
CODING
76.9
Media Cap quality axis
AGENTIC
93.0
Media Cap quality axis
MATH
89.9
Media Cap quality axis
MATRIX OVERALL
66.6
AVG 85.9 across matrix cells
BENCHMARK AVG
81.5
27 tracked scores
STRONGEST SIGNAL
AGENTIC · benchlm
Score 98.9
SPEED · COST · QUALITY
Measured matrix / AA / gateway rows only.
- Overall (Matrix)
- 66.6
- Cap Intelligence
- 88.4
- AA / Intel index
- 39.0
- Cap Coding
- 83.8
- Matrix Coding
- 76.9
- Input $/1M
- $2.50
- Output $/1M
- $15.00
- Value pts/$
- 5.05
DESCRIPTION + DETAILS
OpenAI: GPT-5.4 is a closed model from OpenAI (released 2026-03-05). Context window ~1.1M tokens with capabilities: Vision, Text, Code, Reasoning. List pricing ≈ $2.50 / $15.00 per 1M input/output tokens. Top tracked signals: AGENTIC · benchlm 98.9, MATH · epoch 97.8, GPQA · epoch 94.9. Cadle merges provider listings, unified leaderboard medians, and public pricing where available.
PROVIDER
OpenAI
RELEASE
2026-03-05
CONTEXT
1.1M tokens
STATUS
ACTIVE
COMMUNITY REVIEWS
OPERATOR NOTES
Quality, latency, cost, and failure modes — not marketing copy.
No reviews yet
WRITE A REVIEW
Tap a star to rate
Stored on this device · synced when signed in
No operator notes yet
First review sets the tone for how teams evaluate OpenAI: GPT-5.4.
MODEL COMPARISON
| Metric | |
|---|---|
| Provider | OpenAI |
| Release | 2026-03-05 |
| Input / 1M | $2.50 |
| Output / 1M | $15.00 |
| Context | 1.1M tokens |
| Cadle Cap | 92 |
| Cap board | Cadle Language #29/385 |
| AGENTIC · benchlm | 98.9 |
| MATH · epoch | 97.8 |
| GPQA · epoch | 94.9 |
| REASON · benchlm | 93.7 |
| AGENTIC | 93.0 |
| GPQA · benchlm | 92.8 |
| GPQA | 92.8 |
| GPQA · artificial-analysis | 92.0 |
| MMLU · benchlm | 91.7 |
| MMLU | 91.7 |
| MATH | 89.9 |
| LIVECODEBENCH · benchlm | 87.5 |
DATA PROVENANCE
Scores may use different scales — check the Benchmarks tab for source links.
- OpenRouter / provider APIs (pricing & context)
- Hugging Face Hub (downloads & cards)
- Papers With Code (task benchmarks)
- BenchLM.ai (category rollups + atomic benches)
- Epoch AI Benchmarking Hub (ECI + ZIP CSVs)
- LiveCodeBench (generation / execution / repair / test-output)
- Artificial Analysis (intelligence / indexes)
- LLM Stats (leaderboard + rankings)
- Cadle unified median (equal-weight multi-source)
- Artificial Analysis — throughput, latency, and $/M token snapshots
- Epoch AI Benchmarking Hub — capability CSV exports (when synced)
SOURCE TRACKING
Evidence linked to this model — listing, hub, benchmarks, or live gateway prices.
API
OpenAI listing
API
artificial-analysis
API
OpenRouter
COMMUNITY
Papers with Code
COMMUNITY
BenchLM
COMMUNITY
epoch
COMMUNITY
unified-median
MEASURED CELLS
Same Truth Center numbers as the datasheet above. Accuracy, reliability, safety, and cost scores are not invented.
Overall66.6
AA IQ39
Coding76.9
Agentic93
MMLU91.7
GPQA92.8
Math89.9
LiveCodeBench87.5
ARC-AGI74
AA Index39