Microsoft: Phi 4 wins on more metrics (4 of 5), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | Microsoft: Phi 4 | Reka Flash 3 |
|---|---|---|
| Intelligence Index | 4.9✓ | 4.1 |
| Coding Index | — | — |
| GPQA Diamond | 57%✓ | 53% |
| Design Arena Elo | — | — |
| Speed (tokens/sec) | — | — |
| Latency | — | — |
| Input price /M | $0.070✓ | $0.100 |
| Output price /M | $0.140✓ | $0.200 |
| Context window | 16K | 66K✓ |
| Capabilities | JSON | ReasoningJSON |
Microsoft: Phi 4 wins on more metrics (4 of 5), but the right pick depends on what you optimize for — see the breakdown below.
The table on this page compares Microsoft: Phi 4 and Reka Flash 3 metric by metric — intelligence benchmarks, coding score, speed, latency, context window and per-token price — with the winner marked on each row. Data refreshes hourly.