Compare / head-to-head
Llama 3.3 70B InstructvsPhi-4 Reasoning
Phi-4 Reasoning leads 2 of 2 shared benchmarks. Llama 3.3 70B Instruct has the larger context window (131K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 2
Phi-4 Reasoning leads
Cheaper per token
—
list price, input + output
Larger context
Llama 3.3 70B Instruct
131K tokens
Provider uptime (30d)
— · —
Meta · Microsoft
Llama 3.3 70B Instruct
Meta · released 2024-12-06
text
- Context
- 131K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 5 · 4 core
Phi-4 Reasoning
Microsoft · released 2025-04-30
text
- Context
- 33K
- Max out
- 33K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 4 · 4 core
Quality
Benchmark matrix
2 shared · 2 only Llama 3.3 70B Instruct · 2 only Phi-4 Reasoning| Benchmark | Llama 3.3 70B Instruct | Phi-4 Reasoning | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| GPQA Diamond | 50.5% ↗ | 65.8% ↗ | -15.3 pt | Phi-4 Reasoning |
| MMLU-Pro | 68.9% ↗ | 74.3% ↗ | -5.4 pt | Phi-4 Reasoning |
| Only Llama 3.3 70B Instruct reports · 2 | ||||
| LMArena Elo | 1274 ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 5.1% ↗epoch | not reported | — | — |
| Only Phi-4 Reasoning reports · 2 | ||||
| AIME 2025 | not reported | 62.9% ↗ | — | — |
| HumanEval+ | not reported | 92.9% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Llama 3.3 70B Instruct minus Phi-4 Reasoning in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Llama 3.3 70B Instruct | Phi-4 Reasoning | Edge |
|---|---|---|---|
| Context window | 131K tokens | 33K tokens | Llama 3.3 70B Instruct |
| Max output | — | 33K tokens | — |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text | text | Tie |
| Released | 2024-12-06 | 2025-04-30 | — |
| Cited benchmark scores | 5 | 4 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Llama 3.3 70B Instruct vs …
Models sharing the most benchmarksMore matchups
Phi-4 Reasoning vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Llama 3.3 70B Instruct and Phi-4 Reasoning on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.