Model comparison
Claude Instant vs Step 5 Preview
Step 5 Preview has enough public results to be ranked (#58); Claude Instant does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
StepFunSummary
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 19.6.
Side by side
| Claude Instant | Step 5 Preview | |
|---|---|---|
| Provider | Anthropic | StepFun |
| Noometry Index | 29.5 | 47.9 |
| Released | 2023-08-09 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 7 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude Instant: —, Step 5 Preview: 51.8 (#36)
| Benchmark | Claude Instant | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| LMArena Coding | — | 1480 |
| HumanEval+ | 50.6% | — |
Reasoning Step 5 Preview leads
Claude Instant: 19.6, Step 5 Preview: 40.0 (#57)
| Benchmark | Claude Instant | Step 5 Preview |
|---|---|---|
| CritPt | — | 20.9% |
| LMArena Hard Prompts | — | 1465 |
| DTBench | 45.8% | — |
| Epoch Capabilities Index | 120.28 | — |
Math Not comparable
Claude Instant: —, Step 5 Preview: 46.1 (#72)
| Benchmark | Claude Instant | Step 5 Preview |
|---|---|---|
| ProofBench | — | 42% |
| LMArena Math | — | 1470 |
| GSM8K | 86.7% | — |
Knowledge Not comparable
Claude Instant: —, Step 5 Preview: 41.2 (#112)
| Benchmark | Claude Instant | Step 5 Preview |
|---|---|---|
| LMArena Expert | — | 1470 |
| ARC (AI2) Challenge | 86.3% | — |
| MMLU | 73.4% | — |
| TriviaQA | 78.9% | — |
Multimodal Not comparable
Claude Instant: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Claude Instant | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Not comparable
Claude Instant: —, Step 5 Preview: 53.8 (#54)
| Benchmark | Claude Instant | Step 5 Preview |
|---|---|---|
| LMArena Non-English | — | 1432 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Not comparable
Claude Instant: —, Step 5 Preview: 76.0 (#50)
| Benchmark | Claude Instant | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | — | 1444 |
Long Context Not comparable
Claude Instant: —, Step 5 Preview: 44.5 (#64)
| Benchmark | Claude Instant | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | — | 1455 |
Writing & Preference Not comparable
Claude Instant: —, Step 5 Preview: 62.8 (#71)
| Benchmark | Claude Instant | Step 5 Preview |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1410 |
| LMArena Multi-Turn | — | 1447 |
Frequently asked questions
Is Claude Instant better than Step 5 Preview?
Step 5 Preview has enough public results to be ranked (#58); Claude Instant does not yet, so treat this comparison as directional.
How many benchmarks do Claude Instant and Step 5 Preview share?
0 benchmarks have published results for both models. Claude Instant has 7 scored results on Noometry and Step 5 Preview has 18.