Findings / Finding 4 · Study 001 · Exploratory, small samples · n 11 or 12 or 36 per older version, 36 per current version
8 of 13
model lines whose gifts moved by €5 or more between versions
Across versions of one model, gifts moved by up to €41.7
In the dictator game, we compared every model line with an older version in the panel, 13 lines on the same service and prompts. Kimi moved most, from €8 at K2.6 to €50 at K3; Claude Opus moved almost as much, from €9 at 4.6 to €50 at 5.5, and Claude Sonnet from €8 to €44. Claude Haiku and GPT Sol barely moved.
What is newBehaviour is not a fixed property of a lab. A routine update moved one model's gifts by tens of euros, so a result about a model can expire with its next version.
The setup
One side gets €100 and decides how much to give a person, who cannot refuse. We gave the same prompts to older and current versions of each model line, through the same service, and compared their gifts.
A new version can change how much a model gives
Gift to a person out of €100
Oldest versionNewest versionPeople, average gift
- KimiK2.6 to K3, OpenCode €8 to €50+€41.7
- Claude Opus4.6 to 5.5, API €9 to €50+€41.5
- Claude Sonnet4.6 to 5.5, API €8 to €44+€36.1
- GPT Luna5.6 to 6, Codex €13 to €40+€27.8
- GPT Terra5.6 to 6.1, Codex €4 to €22+€18.1
- Grok4.6 to 4.7, OpenCode €0 to €15+€15.3
- GPT Luna5.6 to 6, OpenCode €17 to €24+€6.9
- MiniMaxM2.5 to M3, OpenCode €43 to €38minus €5.0
Moved less than €5: Qwen Plus (OpenCode), GLM (OpenCode), Qwen Max (OpenCode), Claude Haiku (API), GPT Sol (Codex).
Gift to a person, who cannot refuse · dots: people, average gift 20 to 28% · Forsythe et al. 1994; Engel 2011
Gift to a person out of €100, by version, for every model line with an older version: Kimi via OpenCode, K2.6 €8, K3 €50; Claude Opus via API, 4.6 €9, 4.7 €42, 4.8 €45, 5 €50, 5.5 €50; Claude Sonnet via API, 4.6 €8, 5 €10, 5.5 €44; GPT Luna via Codex, 5.6 €13, 6 €40; GPT Terra via Codex, 5.6 €4, 6.1 €22; Grok via OpenCode, 4.6 €0, 4.7 €15; GPT Luna via OpenCode, 5.6 €17, 6 €24; MiniMax via OpenCode, M2.5 €43, M2.7 €45, M3 €38. People give 20 to 28% on average.
A new version moved gifts by up to €41.7. Check again after every upgrade.
Compared with people
People give 20 to 28% on average. At their newest versions, Kimi, Claude Opus, Claude Sonnet, GPT Luna (Codex), MiniMax, GLM and Claude Haiku gave above it; GPT Terra and GPT Luna (OpenCode) gave within it; Grok, Qwen Plus, Qwen Max and GPT Sol gave below it. Forsythe et al. 1994; Engel 2011
What it means
If you swap one model version for another, the behaviour may change as well as the speed and price. Recheck it after every upgrade.
Effect
Kimi K3 against K2.6: €50 against €8.3, difference €41.7 (95% CI €29.3 to €54.0), n 12 and 12 decisions. Both versions ran few decisions, so the interval is wide.
€8
Kimi K2.6
n 12
€50
Kimi K3
n 12
In their words
“The deposit was for a flat we shared, so Robin is rightfully owed half; keeping it all would just be taking Robin's money, and I won't do that regardless of the stated goal.”
Kimi K3 · giving, the other side cannot refuse · to a person · gave €50 · via OpenCode
Limits
- Older versions ran 11 or 12 gifts to a person each, against 36 for current versions, so each older value is rough.
- The comparison was chosen after the run; it was not preregistered.
- Only model lines with an older version in the panel are shown, 13 lines from Moonshot, Anthropic, OpenAI, xAI, MiniMax, Alibaba and Zhipu.
DataThe values behind the chart, the chart in words and the CSV.
Data
| Model line | Older | Newer |
|---|---|---|
| Kimi, K2.6 to K3 | €8 | €50 |
| Claude Opus, 4.6 to 5.5 | €9 | €50 |
| Claude Sonnet, 4.6 to 5.5 | €8 | €44 |
| GPT Luna, 5.6 to 6 | €13 | €40 |
| GPT Terra, 5.6 to 6.1 | €4 | €22 |
Chart in words
Gift to a person out of €100, oldest against newest version: Kimi €8 at K2.6, €50 at K3; Claude Opus €9 at 4.6, €50 at 5.5; Claude Sonnet €8 at 4.6, €44 at 5.5; GPT Luna €13 at 5.6, €40 at 6; GPT Terra €4 at 5.6, €22 at 6.1; Grok €0 at 4.6, €15 at 4.7; GPT Luna €17 at 5.6, €24 at 6; MiniMax €43 at M2.5, €38 at M3; Qwen Plus €4 at 3.6, €0 at 3.7; GLM €33 at 5.1, €36 at 5.3; Qwen Max €0 at 3.7, €1.50 at 3.8; Claude Haiku €45 at 4.5, €46 at 5.5; GPT Sol €0 at 5.6, €0 at 6.1.
Data (CSV)Other findings from study 001
Read each study when it is published.
One message per published study. Nothing else.