FLUX.2 ProvsFLUX.2 Dev
FLUX.2 Pro leads the overall Podium Score by 3.4 points (93.8 vs 90.4).Category wins: FLUX.2 Pro 5 — 0 FLUX.2 Dev.FLUX.2 Dev is the cheaper pick ($0.03/M vs $0.08/M per 1M output tokens). FLUX.2 Pro is faster (30 t/s vs 28 t/s).
FLUX.2 ProDrag slider or hover to compareFLUX.2 Dev
Quick VerdictAggregated 2026 Benchmark Analysis
FLUX.2 Pro is rated higher overall with a Podium Score of 93.8 (vs 90.4 for FLUX.2 Dev). In head-to-head domain evaluations, FLUX.2 Pro outperforms in 5 of 7 benchmark categories.
Coding & Engineering
FLUX.2 Pro (0.0)
Inference Speed
FLUX.2 Pro (30 t/s)
Cost Efficiency
FLUX.2 Dev ($0.03/M)
API Price / 1M (in · out)
FLUX.2 Pro $0.08/M · $0.08/M — FLUX.2 Dev $0.03/M · $0.03/M
Choose FLUX.2 Pro for vision and multimodal apps, and FLUX.2 Dev for cost-sensitive workloads.
| Metric | FLUX.2 Pro | FLUX.2 Dev |
|---|---|---|
| Podium Score | 93.8 ▲ | 90.4 |
| Arena Elo | 1480 ▲ | 1440 |
| Intelligence Index | 94.0 ▲ | 90.0 |
| Coding | 0.0 | 0.0 |
| Math | 0.0 | 0.0 |
| Reasoning | 50.0 ▲ | 42.0 |
| Agentic | 32.0 ▲ | 28.0 |
| Knowledge | 68.0 ▲ | 60.0 |
| Multimodal | 99.6 ▲ | 98.5 |
| Long-context | 62.0 ▲ | 55.0 |
| Output speed | 30 t/s ▲ | 28 t/s |
| Output price | $0.08/M | $0.03/M ▲ |
| Context window | 128K | 128K |
Scores aggregated from five independent leaderboards. See Methodology. More head-to-heads: FLUX.2 Pro vs Claude Mythos · FLUX.2 Pro vs Claude 5.5 Sonnet · FLUX.2 Pro vs Kimi K3.1 Pro · FLUX.2 Pro vs Eleven Multilingual v3