Compare / head-to-head
Phi-4vsSolar Open 2 250B-A15B
Solar Open 2 250B-A15B leads 2 of 2 shared benchmarks. Solar Open 2 250B-A15B has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 2
Solar Open 2 250B-A15B leads
Cheaper per token
—
list price, input + output
Larger context
Solar Open 2 250B-A15B
1M tokens
Provider uptime (30d)
— · —
Microsoft · Upstage
Phi-4
Microsoft · released 2024-12-12
text
- Context
- 16K
- Max out
- 16K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 11 · 7 core
Solar Open 2 250B-A15B
Upstage · released 2026-07-24
text
- Context
- 1M
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 16 · 5 core
Quality
Benchmark matrix
2 shared · 8 only Phi-4 · 14 only Solar Open 2 250B-A15B| Benchmark | Phi-4 | Solar Open 2 250B-A15B | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| GPQA Diamond | 56.1% ↗ | 86.3% ↗ | -30.2 pt | Solar Open 2 250B-A15B |
| MMLU-Pro | 70.4% ↗ | 86.2% ↗ | -15.8 pt | Solar Open 2 250B-A15B |
| Only Phi-4 reports · 8 | ||||
| MMLU | 84.8% ↗ | not reported | — | — |
| HumanEval | 82.6% ↗ | not reported | — | — |
| LMArena Elo | 1216.6 ↗ | not reported | — | — |
| ArenaHard | 75.4% ↗ | not reported | — | — |
| HumanEval+ | 82.8% ↗ | not reported | — | — |
| IFEval | 63% ↗ | not reported | — | — |
| MATH | 80.4% ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 13.8% ↗epoch | not reported | — | — |
| Only Solar Open 2 250B-A15B reports · 14 | ||||
| SWE-bench Verified | not reported | 70.4% ↗ | — | — |
| AIME 2026 | not reported | 95.7% ↗ | — | — |
| Humanity's Last Exam (no tools) | not reported | 28.8% ↗ | — | — |
| AA-LCR | not reported | 62.3% ↗ | — | — |
| APEX-Agents | not reported | 16.6% ↗ | — | — |
| ArtifactsBench | not reported | 55.9% ↗ | — | — |
| GDPval-AA v2 | not reported | 1128 ↗ | — | — |
| HMMT 2026-02 | not reported | 93.9% ↗ | — | — |
| IFBench | not reported | 80% ↗ | — | — |
| LiveCodeBench v6 | not reported | 92.4% ↗ | — | — |
| MCP Atlas | not reported | 58.2% ↗ | — | — |
| Multi-Challenge | not reported | 61% ↗ | — | — |
| Tau3-Bench (banking) | not reported | 19.6% ↗ | — | — |
| Terminal Bench Hard | not reported | 28.3% ↗ | — | — |
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 Phi-4 minus Solar Open 2 250B-A15B 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 | Phi-4 | Solar Open 2 250B-A15B | Edge |
|---|---|---|---|
| Context window | 16K tokens | 1M tokens | Solar Open 2 250B-A15B |
| Max output | 16K 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 | 2024-12-12 | 2026-07-24 | — |
| Cited benchmark scores | 11 | 16 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Phi-4 vs …
Models sharing the most benchmarksMore matchups
Solar Open 2 250B-A15B vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Phi-4 and Solar Open 2 250B-A15B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.