Model comparison
GPT-5.4 mini vs Grok-2 (Dec 2024)
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 33.7 on the Noometry Index.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. GPT-5.4 mini scores higher in 8 categories and Grok-2 (Dec 2024) in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 mini leads 45.5 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for GPT-5.4 mini and 11.5% for Grok-2 (Dec 2024).
Side by side
| GPT-5.4 mini | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 45.0 | 33.7 |
| Released | 2026-03-17 | 2024-08-13 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.75 | — |
| Output $ / M tokens | $4.50 | — |
| Results tracked | 46 | 34 |
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-2 (Dec 2024): 33.3 (#258)
| Benchmark | GPT-5.4 mini | Grok-2 (Dec 2024) |
|---|---|---|
| WeirdML | 60.3% | 22.2% |
| LMArena Coding | 1438 | 1287 |
| FrontierCode | 27% | — |
| LMArena WebDev | 1397 | — |
| SciCode | 49.9% | — |
| LiveBench Coding | — | 46.4% |
| ALE-Bench | 1,189 | — |
Agentic & Tool Use Not comparable
GPT-5.4 mini: 29.9 (#81), Grok-2 (Dec 2024): —
| Benchmark | GPT-5.4 mini | Grok-2 (Dec 2024) |
|---|---|---|
| DeepResearch Bench | 36.3% | — |
Reasoning GPT-5.4 mini leads
GPT-5.4 mini: 30.4 (#85), Grok-2 (Dec 2024): 16.9 (#299)
| Benchmark | GPT-5.4 mini | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1272 |
| DTBench | 80% | 65.2% |
| Epoch Capabilities Index | 148.84 | 130.48 |
| ARC-AGI-2 | 18.9% | — |
| SimpleBench | — | 22.7% |
| Kagi LLM Benchmark | 37.9% | — |
| NYT Connections (extended) | 61.8% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| LiveBench Reasoning | — | 54.8% |
| Mystery Game Puzzles | 11% | — |
| LiveBench Data Analysis | — | 54.5% |
| LMCA | 40.8% | — |
| ForecastBench | 57 | — |
| LiveBench | — | 54.3% |
Math GPT-5.4 mini leads
GPT-5.4 mini: 45.5 (#75), Grok-2 (Dec 2024): 20.8 (#284)
| Benchmark | GPT-5.4 mini | Grok-2 (Dec 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 11.5% |
| LMArena Math | 1419 | 1283 |
| FrontierMath (Feb 2025 set) | 28.3% | 0.7% |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| ProofBench | 21% | — |
| LiveBench Math | — | 54.9% |
| MATH Level 5 | — | 63.5% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5.4 mini leads
GPT-5.4 mini: 51.5 (#67), Grok-2 (Dec 2024): 29.8 (#233)
| Benchmark | GPT-5.4 mini | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | 86.9% | 53.8% |
| LMArena Expert | 1435 | 1254 |
| SimpleQA Verified | 29.4% | — |
| Confabulations | — | 20.1% |
| Vectara Hallucination Rate | 5.5% | — |
Multimodal Not comparable
GPT-5.4 mini: 39.7 (#56), Grok-2 (Dec 2024): —
| Benchmark | GPT-5.4 mini | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Vision | 1245 | — |
Multilingual GPT-5.4 mini leads
GPT-5.4 mini: 51.9 (#96), Grok-2 (Dec 2024): 43.1 (#188)
| Benchmark | GPT-5.4 mini | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1405 | 1282 |
| LMArena Chinese | 1446 | 1289 |
| LMArena French | 1440 | 1318 |
| LMArena German | 1409 | 1287 |
| LMArena Japanese | 1374 | 1244 |
| LMArena Korean | 1368 | 1237 |
| LMArena Russian | 1417 | 1286 |
| LMArena Spanish | 1405 | 1281 |
Instruction Following GPT-5.4 mini leads
GPT-5.4 mini: 74.1 (#102), Grok-2 (Dec 2024): 66.9 (#202)
| Benchmark | GPT-5.4 mini | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Instruction Following | 1405 | 1270 |
| LiveBench Instruction Following | — | 69.6% |
Long Context GPT-5.4 mini leads
GPT-5.4 mini: 43.0 (#112), Grok-2 (Dec 2024): 38.8 (#190)
| Benchmark | GPT-5.4 mini | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1407 | 1276 |
Writing & Preference GPT-5.4 mini leads
GPT-5.4 mini: 64.0 (#58), Grok-2 (Dec 2024): 48.6 (#198)
| Benchmark | GPT-5.4 mini | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1412 | 1305 |
| LMArena Creative Writing | 1370 | 1284 |
| LMArena Multi-Turn | 1429 | 1290 |
| Short-Story Creative Writing | — | 63.6% |
| EQ-Bench Creative Writing | 1665 | — |
| LiveBench Language | — | 45.6% |
Frequently asked questions
Is GPT-5.4 mini better than Grok-2 (Dec 2024)?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 33.7 on the Noometry Index.
Is GPT-5.4 mini or Grok-2 (Dec 2024) better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 33.3 in the Noometry coding category.
How many benchmarks do GPT-5.4 mini and Grok-2 (Dec 2024) share?
23 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Grok-2 (Dec 2024) has 34.