Model comparison
GPT-5.4 mini vs Grok 4.3
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 43.8 on the Noometry Index.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. GPT-5.4 mini scores higher in 7 categories and Grok 4.3 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where GPT-5.4 mini leads 39.7 to 31.6.
- The biggest single-benchmark swing is DTBench: 80% for GPT-5.4 mini and 90.7% for Grok 4.3.
- Grok 4.3 is cheaper at $1.25 / $2.50 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- Grok 4.3 accepts more context: 1M tokens versus 400K.
Side by side
| GPT-5.4 mini | Grok 4.3 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 45.0 | 43.8 |
| Released | 2026-03-17 | 2026-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1M |
| Max output | 128K | 30K |
| Input $ / M tokens | $0.75 | $1.25 |
| Output $ / M tokens | $4.50 | $2.50 |
| Results tracked | 46 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
GPT-5.4 mini: 45.2 (#72), Grok 4.3: 41.6 (#121)
| Benchmark | GPT-5.4 mini | Grok 4.3 |
|---|---|---|
| LMArena WebDev | 1397 | 1357 |
| SciCode | 49.9% | 47.3% |
| WeirdML | 60.3% | 49.9% |
| LMArena Coding | 1438 | 1415 |
| ALE-Bench | 1,189 | 944.17 |
| FrontierCode | 27% | — |
Agentic & Tool Use GPT-5.4 mini leads
GPT-5.4 mini: 29.9 (#81), Grok 4.3: 27.7 (#99)
| Benchmark | GPT-5.4 mini | Grok 4.3 |
|---|---|---|
| DeepResearch Bench | 36.3% | — |
| GDP.pdf | — | 8% |
| LMArena Search | — | 1165 |
| Vending-Bench 2 | — | 35.26 |
Reasoning Grok 4.3 leads
GPT-5.4 mini: 30.4 (#85), Grok 4.3: 35.9 (#68)
| Benchmark | GPT-5.4 mini | Grok 4.3 |
|---|---|---|
| NYT Connections (extended) | 61.8% | 55.2% |
| CritPt | 10% | 8% |
| Chess Puzzles | 24% | 25% |
| LMArena Hard Prompts | 1424 | 1396 |
| DTBench | 80% | 90.7% |
| LMCA | 40.8% | 38.3% |
| Epoch Capabilities Index | 148.84 | 149.16 |
| ForecastBench | 57 | 60.3 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| ARC-AGI-1 | 63.7% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
Math Too close to call
GPT-5.4 mini: 45.5 (#75), Grok 4.3: 46.0 (#74)
| Benchmark | GPT-5.4 mini | Grok 4.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 42.8% |
| FrontierMath Tier 4 | 9.8% | 14.6% |
| OTIS Mock AIME 2024-2025 | 88.9% | 93.3% |
| ProofBench | 21% | 11% |
| LMArena Math | 1419 | 1388 |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Grok 4.3 leads
GPT-5.4 mini: 51.5 (#67), Grok 4.3: 52.5 (#62)
| Benchmark | GPT-5.4 mini | Grok 4.3 |
|---|---|---|
| GPQA Diamond | 86.9% | 88.8% |
| SimpleQA Verified | 29.4% | 33.2% |
| LMArena Expert | 1435 | 1385 |
| Vectara Hallucination Rate | 5.5% | — |
Multimodal GPT-5.4 mini leads
GPT-5.4 mini: 39.7 (#56), Grok 4.3: 31.6 (#104)
| Benchmark | GPT-5.4 mini | Grok 4.3 |
|---|---|---|
| LMArena Vision | 1245 | 1229 |
| Blueprint-Bench 2 | — | 0% |
Multilingual GPT-5.4 mini leads
GPT-5.4 mini: 51.9 (#96), Grok 4.3: 50.5 (#120)
| Benchmark | GPT-5.4 mini | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1405 | 1385 |
| LMArena Chinese | 1446 | 1422 |
| LMArena French | 1440 | 1412 |
| LMArena German | 1409 | 1395 |
| LMArena Japanese | 1374 | 1379 |
| LMArena Korean | 1368 | 1356 |
| LMArena Russian | 1417 | 1399 |
| LMArena Spanish | 1405 | 1398 |
Instruction Following GPT-5.4 mini leads
GPT-5.4 mini: 74.1 (#102), Grok 4.3: 72.1 (#140)
| Benchmark | GPT-5.4 mini | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1366 |
Long Context Too close to call
GPT-5.4 mini: 43.0 (#112), Grok 4.3: 42.5 (#123)
| Benchmark | GPT-5.4 mini | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1407 | 1393 |
Writing & Preference GPT-5.4 mini leads
GPT-5.4 mini: 64.0 (#58), Grok 4.3: 58.5 (#118)
| Benchmark | GPT-5.4 mini | Grok 4.3 |
|---|---|---|
| LMArena Text | 1412 | 1397 |
| LMArena Creative Writing | 1370 | 1380 |
| LMArena Multi-Turn | 1429 | 1406 |
| EQ-Bench Creative Writing | 1665 | — |
| EQ-Bench 4 | — | 1075 |
Frequently asked questions
Is GPT-5.4 mini better than Grok 4.3?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 43.8 on the Noometry Index.
Which is cheaper, GPT-5.4 mini or Grok 4.3?
Grok 4.3 is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.
Is GPT-5.4 mini or Grok 4.3 better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 41.6 in the Noometry coding category.
Which has the bigger context window?
Grok 4.3 does, with 1M tokens against 400K.
How many benchmarks do GPT-5.4 mini and Grok 4.3 share?
35 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Grok 4.3 has 40.