Model comparison
GPT-4 Turbo vs Laguna M.1
Laguna M.1 is the stronger model overall, scoring 32.5 to 30.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
PoolsideSummary
- The widest gap is in math, where Laguna M.1 leads 21.1 to 9.0.
- Laguna M.1 accepts more context: 262K tokens versus 128K.
- Laguna M.1 has downloadable open weights; the other is API-only.
Side by side
| GPT-4 Turbo | Laguna M.1 | |
|---|---|---|
| Provider | OpenAI | Poolside |
| Noometry Index | 30.5 | 32.5 |
| Released | 2023-11-06 | 2026-04-28 |
| Weights | Proprietary | Open |
| Context window | 128K | 262K |
| Max output | 4K | 33K |
| Input $ / M tokens | $10 | — |
| Output $ / M tokens | $30 | — |
| Results tracked | 36 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Laguna M.1 leads
GPT-4 Turbo: 33.8 (#249), Laguna M.1: 36.6 (#204)
| Benchmark | GPT-4 Turbo | Laguna M.1 |
|---|---|---|
| LMArena WebDev | — | 1349 |
| WeirdML | 18% | — |
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1268 | — |
| BigCodeBench Complete | 58.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, Laguna M.1: —
| Benchmark | GPT-4 Turbo | Laguna M.1 |
|---|---|---|
| METR Time Horizons | 36.7% | — |
Reasoning Laguna M.1 leads
GPT-4 Turbo: 15.3 (#317), Laguna M.1: 23.1 (#184)
| Benchmark | GPT-4 Turbo | Laguna M.1 |
|---|---|---|
| SimpleBench | 25.1% | — |
| Chess Puzzles | 6% | — |
| LMArena Hard Prompts | 1251 | — |
| DTBench | 61.6% | — |
| LMCA | 9.8% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 127.25 | — |
| ForecastBench | 59.4 | — |
Math Laguna M.1 leads
GPT-4 Turbo: 9.0 (#322), Laguna M.1: 21.1 (#283)
| Benchmark | GPT-4 Turbo | Laguna M.1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| ProofBench | — | 0% |
| LMArena Math | 1272 | — |
| MATH Level 5 | 46.7% | — |
Knowledge Not comparable
GPT-4 Turbo: 24.3 (#268), Laguna M.1: —
| Benchmark | GPT-4 Turbo | Laguna M.1 |
|---|---|---|
| GPQA Diamond | 46.6% | — |
| Confabulations | 28.4% | — |
| LMArena Expert | 1223 | — |
| MMLU | 81.3% | — |
Multimodal Not comparable
GPT-4 Turbo: 30.6 (#110), Laguna M.1: —
| Benchmark | GPT-4 Turbo | Laguna M.1 |
|---|---|---|
| LMArena Vision | 1090 | — |
Multilingual Not comparable
GPT-4 Turbo: 40.5 (#216), Laguna M.1: —
| Benchmark | GPT-4 Turbo | Laguna M.1 |
|---|---|---|
| LMArena Non-English | 1245 | — |
| LMArena Chinese | 1242 | — |
| LMArena French | 1276 | — |
| LMArena German | 1259 | — |
| LMArena Japanese | 1194 | — |
| LMArena Korean | 1187 | — |
| LMArena Russian | 1259 | — |
| LMArena Spanish | 1260 | — |
Instruction Following Not comparable
GPT-4 Turbo: 65.8 (#216), Laguna M.1: —
| Benchmark | GPT-4 Turbo | Laguna M.1 |
|---|---|---|
| LMArena Instruction Following | 1249 | — |
Long Context Not comparable
GPT-4 Turbo: 38.0 (#206), Laguna M.1: —
| Benchmark | GPT-4 Turbo | Laguna M.1 |
|---|---|---|
| LMArena Longer Query | 1254 | — |
Writing & Preference Not comparable
GPT-4 Turbo: 47.7 (#206), Laguna M.1: —
| Benchmark | GPT-4 Turbo | Laguna M.1 |
|---|---|---|
| LMArena Text | 1272 | — |
| LMArena Creative Writing | 1269 | — |
| LMArena Multi-Turn | 1267 | — |
Frequently asked questions
Is GPT-4 Turbo better than Laguna M.1?
Laguna M.1 is the stronger model overall, scoring 32.5 to 30.5 on the Noometry Index.
Is GPT-4 Turbo or Laguna M.1 better for coding?
Laguna M.1 scores higher on coding benchmarks: 36.6 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Laguna M.1 does, with 262K tokens against 128K.
How many benchmarks do GPT-4 Turbo and Laguna M.1 share?
0 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Laguna M.1 has 3.