Model comparison
Command R+ vs GPT-5.4 mini
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 32.4 on the Noometry Index.
Last verified . 21 shared benchmarks.
CohereSummary
- They share 21 benchmarks with published results for both. Command R+ scores higher in 0 categories and GPT-5.4 mini in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 mini leads 30.4 to 9.2.
- The biggest single-benchmark swing is LMCA: 5% for Command R+ and 40.8% for GPT-5.4 mini.
- GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $2.50 / $10 for Command R+.
- GPT-5.4 mini accepts more context: 400K tokens versus 128K.
- Command R+ has downloadable open weights; the other is API-only.
Side by side
| Command R+ | GPT-5.4 mini | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 32.4 | 45.0 |
| Released | 2024-08-30 | 2026-03-17 |
| Weights | Open | Proprietary |
| Context window | 128K | 400K |
| Max output | 4K | 128K |
| Input $ / M tokens | $2.50 | $0.75 |
| Output $ / M tokens | $10 | $4.50 |
| Results tracked | 34 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
Command R+: 29.1 (#309), GPT-5.4 mini: 45.2 (#72)
| Benchmark | Command R+ | GPT-5.4 mini |
|---|---|---|
| LMArena Coding | 1187 | 1438 |
| FrontierCode | — | 27% |
| LMArena WebDev | — | 1397 |
| SciCode | — | 49.9% |
| WeirdML | — | 60.3% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| ALE-Bench | — | 1,189 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, GPT-5.4 mini: 29.9 (#81)
| Benchmark | Command R+ | GPT-5.4 mini |
|---|---|---|
| DeepResearch Bench | — | 36.3% |
Reasoning GPT-5.4 mini leads
Command R+: 9.2 (#344), GPT-5.4 mini: 30.4 (#85)
| Benchmark | Command R+ | GPT-5.4 mini |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1424 |
| DTBench | 54.9% | 80% |
| LMCA | 5% | 40.8% |
| Epoch Capabilities Index | 119.34 | 148.84 |
| ARC-AGI-2 | — | 18.9% |
| SimpleBench | 17.4% | — |
| 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 | 24.8% | — |
| Mystery Game Puzzles | — | 11% |
| LiveBench Data Analysis | 38.1% | — |
| ForecastBench | — | 57 |
| LiveBench | 31.8% | — |
Math GPT-5.4 mini leads
Command R+: 28.9 (#242), GPT-5.4 mini: 45.5 (#75)
| Benchmark | Command R+ | GPT-5.4 mini |
|---|---|---|
| LMArena Math | 1188 | 1419 |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 21% |
| LiveBench Math | 21.3% | — |
| FrontierMath (Feb 2025 set) | — | 28.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GPT-5.4 mini leads
Command R+: 36.4 (#169), GPT-5.4 mini: 51.5 (#67)
| Benchmark | Command R+ | GPT-5.4 mini |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 5.5% |
| LMArena Expert | 1174 | 1435 |
| GPQA Diamond | — | 86.9% |
| SimpleQA Verified | — | 29.4% |
| MMLU | 69.4% | — |
Multimodal Not comparable
Command R+: —, GPT-5.4 mini: 39.7 (#56)
| Benchmark | Command R+ | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual GPT-5.4 mini leads
Command R+: 38.6 (#227), GPT-5.4 mini: 51.9 (#96)
| Benchmark | Command R+ | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1216 | 1405 |
| LMArena Chinese | 1226 | 1446 |
| LMArena French | 1209 | 1440 |
| LMArena German | 1216 | 1409 |
| LMArena Japanese | 1166 | 1374 |
| LMArena Korean | 1138 | 1368 |
| LMArena Russian | 1227 | 1417 |
| LMArena Spanish | 1189 | 1405 |
Instruction Following GPT-5.4 mini leads
Command R+: 60.0 (#254), GPT-5.4 mini: 74.1 (#102)
| Benchmark | Command R+ | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1197 | 1405 |
| LiveBench Instruction Following | 57.6% | — |
Long Context GPT-5.4 mini leads
Command R+: 37.3 (#219), GPT-5.4 mini: 43.0 (#112)
| Benchmark | Command R+ | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1230 | 1407 |
Writing & Preference GPT-5.4 mini leads
Command R+: 43.5 (#228), GPT-5.4 mini: 64.0 (#58)
| Benchmark | Command R+ | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1229 | 1412 |
| LMArena Creative Writing | 1235 | 1370 |
| LMArena Multi-Turn | 1213 | 1429 |
| EQ-Bench Creative Writing | — | 1665 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than GPT-5.4 mini?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 32.4 on the Noometry Index.
Which is cheaper, Command R+ or GPT-5.4 mini?
GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or GPT-5.4 mini better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 29.1 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 Command R+ and GPT-5.4 mini share?
21 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and GPT-5.4 mini has 46.