Model comparison
GPT-5.4 mini vs Grok 4.1 Fast
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 41.4 on the Noometry Index. Grok 4.1 Fast costs 6.1× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. GPT-5.4 mini scores higher in 8 categories and Grok 4.1 Fast in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 33.1.
- The biggest single-benchmark swing is NYT Connections (extended): 61.8% for GPT-5.4 mini and 87.4% for Grok 4.1 Fast.
- Grok 4.1 Fast is cheaper at $0.20 / $0.50 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- GPT-5.4 mini accepts more context: 400K tokens versus 128K.
Side by side
| GPT-5.4 mini | Grok 4.1 Fast | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 45.0 | 41.4 |
| Released | 2026-03-17 | 2025-06-27 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 128K |
| Max output | 128K | 30K |
| Input $ / M tokens | $0.75 | $0.20 |
| Output $ / M tokens | $4.50 | $0.50 |
| Results tracked | 46 | 32 |
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 4.1 Fast: 34.1 (#245)
| Benchmark | GPT-5.4 mini | Grok 4.1 Fast |
|---|---|---|
| LMArena WebDev | 1397 | 1242 |
| LMArena Coding | 1438 | 1411 |
| ALE-Bench | 1,189 | 394.93 |
| FrontierCode | 27% | — |
| SciCode | 49.9% | — |
| WeirdML | 60.3% | — |
Agentic & Tool Use Grok 4.1 Fast leads
GPT-5.4 mini: 29.9 (#81), Grok 4.1 Fast: 36.3 (#39)
| Benchmark | GPT-5.4 mini | Grok 4.1 Fast |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 69.6% |
| τ²-bench Banking | — | 13.1% |
| DeepResearch Bench | 36.3% | — |
| LMArena Search | — | 1171 |
| Vending-Bench 2 | — | 1,107 |
Reasoning Grok 4.1 Fast leads
GPT-5.4 mini: 30.4 (#85), Grok 4.1 Fast: 43.4 (#49)
| Benchmark | GPT-5.4 mini | Grok 4.1 Fast |
|---|---|---|
| NYT Connections (extended) | 61.8% | 87.4% |
| LMArena Hard Prompts | 1424 | 1407 |
| DTBench | 80% | 87.7% |
| ForecastBench | 57 | 61 |
| ARC-AGI-2 | 18.9% | — |
| SimpleBench | — | 56% |
| Kagi LLM Benchmark | 37.9% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
| LMCA | 40.8% | — |
| Epoch Capabilities Index | 148.84 | — |
Math GPT-5.4 mini leads
GPT-5.4 mini: 45.5 (#75), Grok 4.1 Fast: 31.9 (#221)
| Benchmark | GPT-5.4 mini | Grok 4.1 Fast |
|---|---|---|
| ProofBench | 21% | 4% |
| LMArena Math | 1419 | 1408 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| MathArena Final-Answer Competitions | — | 60.9% |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5.4 mini leads
GPT-5.4 mini: 51.5 (#67), Grok 4.1 Fast: 33.1 (#207)
| Benchmark | GPT-5.4 mini | Grok 4.1 Fast |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 17.8% |
| LMArena Expert | 1435 | 1399 |
| GPQA Diamond | 86.9% | — |
| SimpleQA Verified | 29.4% | — |
Multimodal GPT-5.4 mini leads
GPT-5.4 mini: 39.7 (#56), Grok 4.1 Fast: 37.0 (#76)
| Benchmark | GPT-5.4 mini | Grok 4.1 Fast |
|---|---|---|
| LMArena Vision | 1245 | 1201 |
Multilingual Too close to call
GPT-5.4 mini: 51.9 (#96), Grok 4.1 Fast: 51.0 (#114)
| Benchmark | GPT-5.4 mini | Grok 4.1 Fast |
|---|---|---|
| LMArena Non-English | 1405 | 1391 |
| LMArena Chinese | 1446 | 1441 |
| LMArena French | 1440 | 1415 |
| LMArena German | 1409 | 1404 |
| LMArena Japanese | 1374 | 1349 |
| LMArena Korean | 1368 | 1361 |
| LMArena Russian | 1417 | 1387 |
| LMArena Spanish | 1405 | 1413 |
Instruction Following GPT-5.4 mini leads
GPT-5.4 mini: 74.1 (#102), Grok 4.1 Fast: 72.7 (#133)
| Benchmark | GPT-5.4 mini | Grok 4.1 Fast |
|---|---|---|
| LMArena Instruction Following | 1405 | 1376 |
Long Context Too close to call
GPT-5.4 mini: 43.0 (#112), Grok 4.1 Fast: 42.4 (#126)
| Benchmark | GPT-5.4 mini | Grok 4.1 Fast |
|---|---|---|
| LMArena Longer Query | 1407 | 1390 |
Writing & Preference GPT-5.4 mini leads
GPT-5.4 mini: 64.0 (#58), Grok 4.1 Fast: 57.2 (#131)
| Benchmark | GPT-5.4 mini | Grok 4.1 Fast |
|---|---|---|
| LMArena Text | 1412 | 1408 |
| LMArena Creative Writing | 1370 | 1394 |
| EQ-Bench Creative Writing | 1665 | 1327 |
| LMArena Multi-Turn | 1429 | 1389 |
Frequently asked questions
Is GPT-5.4 mini better than Grok 4.1 Fast?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 41.4 on the Noometry Index. Grok 4.1 Fast costs 6.1× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Which is cheaper, GPT-5.4 mini or Grok 4.1 Fast?
Grok 4.1 Fast is cheaper. It lists at $0.20 per million input tokens and $0.50 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.
Is GPT-5.4 mini or Grok 4.1 Fast better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 mini does, with 400K tokens against 128K.
How many benchmarks do GPT-5.4 mini and Grok 4.1 Fast share?
26 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Grok 4.1 Fast has 32.