US dollars per euro · EUR/USD
Forecast outcome — 30 Sep 2026
Forecast issued on 31 Jul 2026, 06:12 UTC
61 days before the target. This is the scored version, chosen by the documented evaluation rule. The original estimates below are unchanged.
Result
- Original reference
- 1.1480
- Observed ECB fixing, Thursday, 30 Jul 2026
- Target observation
- 1.1455
- ECB fixing, Wednesday, 30 Sep 2026 · ECB daily reference rate
- Realized return
- −0.22%
- Price at the target versus the reference
- Outcome at ±1%
- Between −1% and +1%
- 1.1365 to 1.1595
- Outcome at ±5%
- Between −5% and +5%
- 1.0906 to 1.2054
- Outcome at ±10%
- Between −10% and +10%
- 1.0332 to 1.2628
- Outcome at ±50%
- Between −50% and +50%
- 0.5740 to 1.7220
One outcome is scored at each threshold. The page keeps all four.
Original forecast · AI average — uncalibrated
As published on 31 Jul 2026. Nothing here has been rewritten after the outcome.
Down 1% or more
36%
1.1365 or lower
Did not happen
Between −1% and +1%
20%
1.1365 to 1.1595
Happened
Up 1% or more
44%
1.1595 or higher
Did not happen
The forecast put 20% on the outcome that happened.
Down 5% or more
9%
1.0906 or lower
Did not happen
Between −5% and +5%
77%
1.0906 to 1.2054
Happened
Up 5% or more
14%
1.2054 or higher
Did not happen
The forecast put 77% on the outcome that happened.
Down 10% or more
1%
1.0332 or lower
Did not happen
Between −10% and +10%
97%
1.0332 to 1.2628
Happened
Up 10% or more
2%
1.2628 or higher
Did not happen
The forecast put 97% on the outcome that happened.
Down 50% or more
<0.1%
0.5740 or lower
Did not happen
Between −50% and +50%
>99.9%
0.5740 to 1.7220
Happened
Up 50% or more
<0.1%
1.7220 or higher
Did not happen
The forecast put >99.9% on the outcome that happened.
Outcome at every threshold
The realized return of −0.22% falls into a different category depending on the threshold.
| Threshold | Outcome | Original Down / Within / Up | On outcome | Brier (0–2) |
|---|---|---|---|---|
| ±1% | Between −1% and +1% 1.1365 to 1.1595 | 36% / 20% / 44% | 20% | 0.975 |
| ±5% | Between −5% and +5% 1.0906 to 1.2054 | 9% / 77% / 14% | 77% | 0.083 |
| ±10% | Between −10% and +10% 1.0332 to 1.2628 | 1% / 97% / 2% | 97% | 0.002 |
| ±50% | Between −50% and +50% 0.5740 to 1.7220 | <0.1% / >99.9% / <0.1% | >99.9% | 0.000 |
Values shown as <0.1% or >99.9% are rounded for display; the underlying values sum to 100%.
Scores by source
At ±1%, same scored version and the same outcome. Differences on a single result are not evidence that one source is better.
| Source | Original Down / Within / Up | Brier (0–2) |
|---|---|---|
| AI average | 36% / 20% / 44% | 0.975 |
| OpenAI | 33% / 19% / 48% | 1.005 |
| Claude | 39% / 21% / 40% | 0.950 |
| Statistical reference Synthetic fixture | 38% / 24% / 38% | 0.869 |
| Prediction markets | No matching market | Not scored |
At ±5%, same scored version and the same outcome. Differences on a single result are not evidence that one source is better.
| Source | Original Down / Within / Up | Brier (0–2) |
|---|---|---|
| AI average | 9% / 77% / 14% | 0.083 |
| OpenAI | 9% / 74% / 17% | 0.101 |
| Claude | 10% / 79% / 11% | 0.067 |
| Statistical reference Synthetic fixture | 6% / 87% / 7% | 0.025 |
| Prediction markets | No matching market | Not scored |
At ±10%, same scored version and the same outcome. Differences on a single result are not evidence that one source is better.
| Source | Original Down / Within / Up | Brier (0–2) |
|---|---|---|
| AI average | 1% / 97% / 2% | 0.002 |
| OpenAI | 1% / 96% / 3% | 0.003 |
| Claude | 1% / 97% / 2% | 0.001 |
| Statistical reference Synthetic fixture | 0.1% / 99.7% / 0.2% | 0.000 |
| Prediction markets | No matching market | Not scored |
At ±50%, same scored version and the same outcome. Differences on a single result are not evidence that one source is better.
| Source | Original Down / Within / Up | Brier (0–2) |
|---|---|---|
| AI average | <0.1% / >99.9% / <0.1% | 0.000 |
| OpenAI | <0.1% / >99.9% / <0.1% | 0.000 |
| Claude | <0.1% / >99.9% / <0.1% | 0.000 |
| Statistical reference Synthetic fixture | <0.1% / 100.0% / 0.0% | 0.000 |
| Prediction markets | No matching market | Not scored |
Which version is scored
One version was published for this date. The evaluation rule picks the scored version per target in advance, so the score never depends on which version happened to look best. Evaluation rules
| Issued | Lead time | Reference | ±1% Down / Within / Up | Evaluation |
|---|---|---|---|---|
| 31 Jul 2026, 06:12 UTC | 61 days | 1.1480 30 Jul fixing | 36% / 20% / 44% | Scored version |
Each stored version keeps its own reference price and timestamps.