Model comparison
GPT-5.6 Terra vs Reka Flash 3
GPT-5.6 Terra has enough public results to be ranked (#15); Reka Flash 3 does not yet, so treat this comparison as directional.
Last verified . 2 shared benchmarks.
Summary
- They share 2 benchmarks with published results for both. GPT-5.6 Terra scores higher in 2 categories and Reka Flash 3 in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5.6 Terra leads 70.4 to 43.8.
- The biggest single-benchmark swing is BALROG: 53.2% for GPT-5.6 Terra and 29.2% for Reka Flash 3.
- Reka Flash 3 is cheaper at $0.10 / $0.20 per million input/output tokens, against $2 / $12 for GPT-5.6 Terra.
- GPT-5.6 Terra accepts more context: 1.05M tokens versus 66K.
- Reka Flash 3 has downloadable open weights; the other is API-only.
Side by side
| GPT-5.6 Terra | Reka Flash 3 | |
|---|---|---|
| Provider | OpenAI | Reka |
| Noometry Index | 59.1 | 36.4 |
| Released | 2026-07-09 | 2025-03-10 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 66K |
| Max output | 128K | 59K |
| Input $ / M tokens | $2 | $0.10 |
| Output $ / M tokens | $12 | $0.20 |
| Results tracked | 52 | 2 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.6 Terra: 57.1 (#16), Reka Flash 3: —
| Benchmark | GPT-5.6 Terra | Reka Flash 3 |
|---|---|---|
| DeepSWE | 69.6% | — |
| FrontierCode | 41.3% | — |
| CursorBench | 41.3% | — |
| LMArena WebDev | 1520 | — |
| SciCode | 55% | — |
| WeirdML | 78.3% | — |
| LMArena Coding | 1484 | — |
| ALE-Bench | 1,951 | — |
Agentic & Tool Use GPT-5.6 Terra leads
GPT-5.6 Terra: 40.2 (#23), Reka Flash 3: 30.1
| Benchmark | GPT-5.6 Terra | Reka Flash 3 |
|---|---|---|
| BALROG | 53.2% | 29.2% |
| APEX-Agents | 58.2% | — |
| GDP.pdf | 24.7% | — |
| Vending-Bench 2 | 7,343 | — |
Reasoning Not comparable
GPT-5.6 Terra: 60.6 (#19), Reka Flash 3: —
| Benchmark | GPT-5.6 Terra | Reka Flash 3 |
|---|---|---|
| ARC-AGI-2 | 83.9% | — |
| SimpleBench | 48.9% | — |
| Kagi LLM Benchmark | 51.3% | — |
| NYT Connections (extended) | 78.4% | — |
| ARC-AGI-1 | 96.5% | — |
| CritPt | 30% | — |
| Chess Puzzles | 54% | — |
| LMArena Hard Prompts | 1467 | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 93.3% | — |
| LMCA | 55% | — |
| Surface Evolver Bench | 83.8% | — |
| Epoch Capabilities Index | 159.31 | — |
Math Not comparable
GPT-5.6 Terra: 81.5 (#10), Reka Flash 3: —
| Benchmark | GPT-5.6 Terra | Reka Flash 3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 86% | — |
| FrontierMath Tier 4 | 70.7% | — |
| OTIS Mock AIME 2024-2025 | 99.7% | — |
| ProofBench | 74% | — |
| LMArena Math | 1463 | — |
Knowledge Not comparable
GPT-5.6 Terra: 61.3 (#27), Reka Flash 3: —
| Benchmark | GPT-5.6 Terra | Reka Flash 3 |
|---|---|---|
| GPQA Diamond | 93.3% | — |
| SimpleQA Verified | 43.2% | — |
| LMArena Expert | 1492 | — |
Multimodal Not comparable
GPT-5.6 Terra: 47.5 (#10), Reka Flash 3: —
| Benchmark | GPT-5.6 Terra | Reka Flash 3 |
|---|---|---|
| LMArena Vision | 1271 | — |
| Blueprint-Bench 2 | 30.8% | — |
| Furniture Assembly | 54.2% | — |
| LMArena Document | 1472 | — |
Multilingual Not comparable
GPT-5.6 Terra: 54.5 (#42), Reka Flash 3: —
| Benchmark | GPT-5.6 Terra | Reka Flash 3 |
|---|---|---|
| LMArena Non-English | 1439 | — |
| LMArena Chinese | 1514 | — |
| LMArena French | 1476 | — |
| LMArena German | 1462 | — |
| LMArena Japanese | 1446 | — |
| LMArena Korean | 1420 | — |
| LMArena Russian | 1450 | — |
| LMArena Spanish | 1455 | — |
Instruction Following Not comparable
GPT-5.6 Terra: 76.6 (#38), Reka Flash 3: —
| Benchmark | GPT-5.6 Terra | Reka Flash 3 |
|---|---|---|
| LMArena Instruction Following | 1453 | — |
Long Context Not comparable
GPT-5.6 Terra: 44.4 (#64), Reka Flash 3: —
| Benchmark | GPT-5.6 Terra | Reka Flash 3 |
|---|---|---|
| LMArena Longer Query | 1452 | — |
Writing & Preference GPT-5.6 Terra leads
GPT-5.6 Terra: 70.4 (#21), Reka Flash 3: 43.8
| Benchmark | GPT-5.6 Terra | Reka Flash 3 |
|---|---|---|
| EQ-Bench Creative Writing | 1855 | 1228 |
| LMArena Text | 1446 | — |
| LMArena Creative Writing | 1411 | — |
| EQ-Bench 4 | 1234 | — |
| LMArena Multi-Turn | 1451 | — |
Frequently asked questions
Is GPT-5.6 Terra better than Reka Flash 3?
GPT-5.6 Terra has enough public results to be ranked (#15); Reka Flash 3 does not yet, so treat this comparison as directional.
Which is cheaper, GPT-5.6 Terra or Reka Flash 3?
Reka Flash 3 is cheaper. It lists at $0.10 per million input tokens and $0.20 per million output tokens; GPT-5.6 Terra lists at $2 and $12.
Which has the bigger context window?
GPT-5.6 Terra does, with 1.05M tokens against 66K.
How many benchmarks do GPT-5.6 Terra and Reka Flash 3 share?
2 benchmarks have published results for both models. GPT-5.6 Terra has 52 scored results on Noometry and Reka Flash 3 has 2.